clulab_publications.bib

@inproceedings{rezaei-blanco-2024-paraphrasing,
  author    = {Rezaei, MohammadHossein  and  Blanco, Eduardo},
  title     = {Making Language Models Robust Against Negation},
  booktitle      = {Proceedings of the 2025 Conference of the Nations of America Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month          = {April},
  year           = {2025},
  address        = {Albuquerque, New Mexico, USA},
  publisher      = {Association for Computational Linguistics},
  pages     = {},
  abstract  = {Negation has been a long-standing challenge for language models. Previous studies have shown that they struggle with negation in many natural language understanding tasks. In this work, we propose a self-supervised method to make language models more robust against negation. We introduce a novel task, Next Sentence Polarity Prediction (NSPP), and a variation of the Next Sentence Prediction (NSP) task. We show that RoBERTa and BERT further pre-trained on our tasks outperform the off-the-shelf transformer models on eight negation-related benchmarks. Most notably, the pretrainings yield between 1.8% and 9.1% improvement on CondaQA, a large question-answering corpus requiring reasoning over negation.},
  url       = {https://arxiv.org/pdf/2502.07717}
}

@inproceedings{negru-et-al-naacl2025-morphnli,
    title = "MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing",
    author = "Vlad Negru and Robert Vacareanu and Camelia Lemnaru and Mihai Surdeanu and Rodica Potolea",
    booktitle = "Findings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)",
    year = "2025",
    url = "https://arxiv.org/abs/2502.09567",
    abstract = "We introduce MorphNLI, a modular step-by-step approach to natural language inference (NLI). When classifying the premise-hypothesis pairs into {entailment, contradiction, neutral}, we use a language model to generate the necessary edits to incrementally transform (i.e., morph) the premise into the hypothesis. Then, using an off-the-shelf NLI model we track how the entailment progresses with these atomic changes, aggregating these intermediate labels into a final output. We demonstrate the advantages of our proposed method particularly in realistic cross-domain settings, where our method always outperforms strong baselines with improvements up to 12.6% (relative). Further, our proposed approach is explainable as the atomic edits can be used to understand the overall NLI label.",
}

@inproceedings{noriega-atala-etal-2024-happen,
    title = "When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context",
    author = "Noriega-Atala, Enrique  and
      Vacareanu, Robert  and
      Ashton, Salena Torres  and
      Pyarelal, Adarsh  and
      Morrison, Clayton T  and
      Surdeanu, Mihai",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.219/",
    doi = "10.18653/v1/2024.findings-emnlp.219",
    pages = "3821--3829",
    abstract = "We introduce a neural architecture finetuned for the task of scenario context generation: The relevant location and time of an event or entity mentioned in text. Contextualizing information extraction helps to scope the validity of automated finings when aggregating them as knowledge graphs. Our approach uses a high-quality curated dataset of time and location annotations in a corpus of epidemiology papers to train an encoder-decoder architecture. We also explored the use of data augmentation techniques during training. Our findings suggest that a relatively small fine-tuned encoder-decoder model performs better than out-of-the-box LLMs and semantic role labeling parsers to accurate predict the relevant scenario information of a particular entity or event."
}

@misc{cooper2024findingwolfsheepsclothing,
      title={Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization}, 
      author={Portia Cooper and Harshita Narnoli and Mihai Surdeanu},
      year={2024},
      eprint={2412.12212},
      archivePrefix={arXiv},
      primaryClass={cs.CR},
      url={https://arxiv.org/abs/2412.12212}, 
}

@inproceedings{kwak-et-al-nllp2024-error-analysis,
    title = "Classify First, and Then Extract: Prompt Chaining Technique for Information Extraction",
    author = "Alice Kwak and Clayton Morrison and Derek Bambauer and Mihai Surdeanu",
    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2024",
    month = nov,
    year = "2024",
    url = "https://clulab.org/papers/nllp2024_kwak-et-al.pdf",
    abstract = "This work presents a new task-aware prompt design and example retrieval approach for information extraction (IE) using a prompt chaining technique. Our approach divides IE tasks into two steps: (1) text classification to understand what information (e.g., entity or event types) is contained in the underlying text and (2) information extraction for the identified types. Initially, we use a large language model (LLM) in a few-shot setting to classify the contained information. The classification output is used to select the relevant prompt and retrieve the examples relevant to the input text. Finally, we ask a LLM to do the information extraction with the generated prompt. By evaluating our approach on legal IE tasks with two different LLMs, we demonstrate that the prompt chaining technique improves the LLM’s overall performance in a few-shot setting when compared to the baseline in which examples from all possible classes are included in the prompt. Our approach can be used in a low-resource setting as it does not require a large amount of training data. Also, it can be easily adapted to many different IE tasks by simply adjusting the prompts. Lastly, it provides a cost benefit by reducing the number of tokens in the prompt.",
}

@inproceedings{singh-2024-learning,
    title = "Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach",
    author = "Singh, Mayank and Blanco, Eduardo",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, USA and virtual meeting",
    publisher = "Association for Computational Linguistics",
    abstract = "We propose a neuro-symbolic approach for realistic few-shot relation classification via rules. Instead of building neural models to predict relations, we design them to output straightforward rules that can be used to extract relations. The rules are generated using custom T5-style Encoder-Decoder Language Models. Crucially, our rules are fully interpretable and pliable (i.e., humans can easily modify them to boost performance). Through a combination of rules generated by these models along with a very effective, novel baseline, we demonstrate a few-shot relation-classification performance that is comparable to or stronger than the state of the art on the Few-Shot TACRED and NYT29 benchmarks while increasing interpretability and maintaining pliability.",
}

@inproceedings{rezaei-blanco-2024-paraphrasing,
    title = "Paraphrasing in Affirmative Terms Improves Negation Understanding",
    author = "Rezaei, MohammadHossein  and
      Blanco, Eduardo",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-short.55/",
    doi = "10.18653/v1/2024.acl-short.55",
    pages = "602--615",
    abstract = "Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.e., paraphrases without negation) to make models more robust against negation. Crucially, our affirmative interpretations are obtained automatically. We show improvements with CondaQA, a large corpus requiring reasoning with negation, and five natural language understanding tasks."
}

@inproceedings{sanayei-etal-2024-maria,
    title = "{MAR}i{A} at {S}em{E}val 2024 Task-6: Hallucination Detection Through {LLM}s, {MNLI}, and Cosine similarity",
    author = "Sanayei, Reza  and
      Singh, Abhyuday  and
      Rezaei, Mohammadhossein  and
      Bethard, Steven",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.semeval-1.225",
    pages = "1584--1588",
    abstract = "The advent of large language models (LLMs) has revolutionized Natural Language Generation (NLG), offering unmatched text generation capabilities. However, this progress introduces significant challenges, notably hallucinations{---}semantically incorrect yet fluent outputs. This phenomenon undermines content reliability, as traditional detection systems focus more on fluency than accuracy, posing a risk of misinformation spread.Our study addresses these issues by proposing a unified strategy for detecting hallucinations in neural model-generated text, focusing on the SHROOM task in SemEval 2024. We employ diverse methodologies to identify output divergence from the source content. We utilized Sentence Transformers to measure cosine similarity between source-hypothesis and source-target embeddings, experimented with omitting source content in the cosine similarity computations, and Leveragied LLMs{'} In-Context Learning with detailed task prompts as our methodologies. The varying performance of our different approaches across the subtasks underscores the complexity of Natural Language Understanding tasks, highlighting the importance of addressing the nuances of semantic correctness in the era of advanced language models.",
}

@inproceedings{rezaei-etal-2024-clulab,
    title = "{CLUL}ab-{U}of{A} at {S}em{E}val-2024 Task 8: Detecting Machine-Generated Text Using Triplet-Loss-Trained Text Similarity and Text Classification",
    author = "Rezaei, Mohammadhossein  and
      Kwon, Yeaeun  and
      Sanayei, Reza  and
      Singh, Abhyuday  and
      Bethard, Steven",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.semeval-1.215",
    pages = "1498--1504",
    abstract = "Detecting machine-generated text is a critical task in the era of large language models. In this paper, we present our systems for SemEval-2024 Task 8, which focuses on multi-class classification to discern between human-written and maching-generated texts by five state-of-the-art large language models. We propose three different systems: unsupervised text similarity, triplet-loss-trained text similarity, and text classification. We show that the triplet-loss trained text similarity system outperforms the other systems, achieving 80{\%} accuracy on the test set and surpassing the baseline model for this subtask. Additionally, our text classification system, which takes into account sentence paraphrases generated by the candidate models, also outperforms the unsupervised text similarity system, achieving 74{\%} accuracy.",
}

@inproceedings{
  dumitru2024retrieval,
  title={Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios},
  author={Dumitru, Razvan-Gabriel and Alexeeva, Maria and Alcock, Keith and Ludgate, Nargiza and Jeong, Cheonkam and Abdurahaman, Zara Fatima and Puri, Prateek and Kirchhoff, Brian and Sadhu, Santadarshan and Surdeanu, Mihai},
  booktitle={Sixth Workshop on  NLP and Computational Social Science (at NAACL) 2024},
  year={2024},
  url={http://clulab.org/papers/naacl-css2024-rag.pdf}
}

@article{Vacareanu2024GeneralVerificationLLM,
  title={General Purpose Verification for Chain of Thought Prompting},
  author={Robert Vacareanu and Anurag Pratik and Evangelia Spiliopoulou and Zheng Qi and Giovanni Paolini and Neha Anna John and Jie Ma and Yassine Benajiba and Miguel Ballesteros},
  journal={ArXiv},
  year={2024},
  volume={abs/2405.00204},
  url={https://arxiv.org/pdf/2405.00204.pdf}
}

@article{Vacareanu2024LLMsRegression,
  title={From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples},
  author={Robert Vacareanu and Vlad-Andrei Negru and Vasile Suciu and Mihai Surdeanu},
  journal={ArXiv},
  year={2024},
  volume={abs/2404.07544},
  url={https://arxiv.org/pdf/2404.07544.pdf}
}

@inproceedings{vacareanu2024softrules,
    title = "Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification",
    author = "Robert Vacareanu and Fahmida Alam and Md Asiful Islam and Haris Riaz and Mihai Surdeanu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/pdf/2403.03305.pdf",
    abstract = "This paper introduces a novel neuro-symbolic architecture for relation classification (RC) that combines rule-based methods with contemporary deep learning techniques. This approach capitalizes on the strengths of both paradigms: the adaptability of rule-based systems and the generalization power of neural networks. Our architecture consists of two components: a declarative rule-based model for transparent classification and a neural component to enhance rule generalizability through semantic text matching. Notably, our semantic matcher is trained in an unsupervised domain-agnostic way, solely with synthetic data. Further, these components are loosely coupled, allowing for rule modifications without retraining the semantic matcher. In our evaluation, we focused on two few-shot relation classification datasets: Few-Shot TACRED and a Few-Shot version of NYT29. We show that our proposed method outperforms previous state-of-the-art models in three out of four settings, despite not seeing any human-annotated training data. Further, we show that our approach remains modular and pliable, i.e., the corresponding rules can be locally modified to improve the overall model. Human interventions to the rules for the TACRED relation \texttt{org:parents} boost the performance on that relation by as much as 26\% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component.",
}

@inproceedings{vacareanu2024ActiveLearningNER,
    title = "Active Learning Design Choices for NER with Transformers",
    author = "Robert Vacareanu and Enrique Noriega-Atala and Gus Hahn-Powell and Marco A. Valenzuela-Escarcega and Mihai Surdeanu ",
    booktitle = "Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation",
    month = may,
    year = "2024",
    address = "Torino, Italy",
    publisher = "European Language Resources Association",
    abstract = "We explore multiple important choices that have not been analyzed in conjunction regarding active learning for token classification using transformer networks. These choices are: (i) how to select what to annotate, (ii) decide whether to annotate entire sentences or smaller sentence fragments, (iii) how to train with incomplete annotations at token-level, and (iv) how to select the initial seed dataset. We explore whether annotating at sub-sentence level can translate to an improved downstream performance by considering two different sub-sentence annotation strategies: (i) entity-level, and (ii) token-level. These approaches result in some sentences being only partially annotated. To address this issue, we introduce and evaluate multiple strategies to deal with partially-annotated sentences during the training process. We show that annotating at the sub-sentence level achieves comparable or better performance than sentence-level annotations with a smaller number of annotated tokens. We then explore the extent to which the performance gap remains once accounting for the annotation time and found that both annotation schemes perform similarly.",
}

@inproceedings{vacareanu-etal-2024-weak,
    title = "A Weak Supervision Approach for Few-Shot Aspect Based Sentiment Analysis",
    author = "Vacareanu, Robert  and
      Varia, Siddharth  and
      Halder, Kishaloy  and
      Wang, Shuai  and
      Paolini, Giovanni  and
      Anna John, Neha  and
      Ballesteros, Miguel  and
      Muresan, Smaranda",
    editor = "Graham, Yvette  and
      Purver, Matthew",
    booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2024",
    address = "St. Julian{'}s, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.eacl-long.167",
    pages = "2734--2752",
    abstract = "We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks. We propose a pipeline approach to construct a noisy ABSA dataset, and we use it to adapt a pre-trained sequence-to-sequence model to the ABSA tasks. We test the resulting model on three widely used ABSA datasets, before and after fine-tuning. Our proposed method preserves the full fine-tuning performance while showing significant improvements (15.84 absolute F1) in the few-shot learning scenario for the harder tasks. In zero-shot (i.e., without fine-tuning), our method outperforms the previous state of the art on the aspect extraction sentiment classification (AESC) task and is, additionally, capable of performing the harder aspect sentiment triplet extraction (ASTE) task.",
}

@inproceedings{wang2024naaclfindings,
    title = "Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains",
    author = "Wang, Zijie and Rashid, Farzana and Blanco, Eduardo",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics"
}

@inproceedings{golchin2024time,
	title={Time Travel in {LLM}s: Tracing Data Contamination in Large Language Models},
	author={Shahriar Golchin and Mihai Surdeanu},
	booktitle={Proceedings of the Twelfth International Conference on Learning Representations (ICLR)},
	year={2024},
	url={https://openreview.net/forum?id=2Rwq6c3tvr}
}

@inproceedings{fahmida2024fs-meta-dataset,
    title = "Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation",
    author = "Fahmida Alam and Md Asiful Islam and Robert Vacareanu and Mihai Surdeanu ",
    booktitle = "Proceedings of the Fourteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2024",
    address = "Torino, Italy",
    publisher = "European Language Resources Association",
    url = "http://arxiv.org/abs/2404.04445",
    abstract = "We introduce a meta dataset for few-shot relation extraction, which includes two datasets derived from existing supervised relation extraction datasets – NYT29 (Takanobu et al. , 2019 ; Nayak and Ng , 2020) and WIKIDATA (Sorokin and Gurevych, 2017) – as well as a few-shot form of the TACRED dataset (Sabo et al., 2021). Importantly, all these few-shot datasets were generated under realistic assumptions such as: the test relations are different from any relations a model might have seen before, limited training data, and a preponderance of candidate relation mentions that do not correspond to any of the relations of interest. Using this large resource, we conduct a comprehensive evaluation of six recent few-shot relation extraction methods, and observe that no method comes out as a clear winner. Further, the overall performance on this task is low, indicating substantial need for future research. We release all versions of the data, i.e., both supervised and few-shot, for future research."
}

@inproceedings{riaz2024ellen,
    title = "ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition",
    author = "Haris Riaz and Razvan-Gabriel Dumitru and Mihai Surdeanu",
    booktitle = "Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation",
    month = may,
    year = "2024",
    address = "Torino, Italy",
    publisher = "European Language Resources Association",
    url = "https://arxiv.org/pdf/2403.17385.pdf",
    abstract = "In this work, we revisit the problem of semi-supervised named entity recognition (NER) focusing on extremely light supervision, consisting of a lexicon containing only 10 examples per class. We introduce ELLEN, a simple, fully modular, neuro-symbolic method that blends fine-tuned language models with linguistic rules. These rules include insights such as ''One Sense Per Discourse'', using a Masked Language Model as an unsupervised NER, leveraging part-of-speech tags to identify and eliminate unlabeled entities as false negatives, and other intuitions about classifier confidence scores in local and global context. ELLEN achieves very strong performance on the CoNLL-2003 dataset when using the minimal supervision from the lexicon above. It also outperforms most existing (and considerably more complex) semi-supervised NER methods under the same supervision settings commonly used in the literature (i.e., 5% of the training data). Further, we evaluate our CoNLL-2003 model in a zero-shot scenario on WNUT-17 where we find that it outperforms GPT-3.5 and achieves comparable performance to GPT-4. In a zero-shot setting, ELLEN also achieves over 75% of the performance of a strong, fully supervised model trained on gold data. Our code is available at: https://github.com/hriaz17/ELLEN",
}

@inproceedings{anaissy-icaart2024,
    title = "On Learning Bipolar Gradual Argumentation Semantics with Neural Networks",
    author = "Caren Al Anaissy and Sandeep Suntwal and Mihai Surdeanu and Srdjan Vesic",
    booktitle = "Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART)",
    year = "2024",
    url = "https://clulab.org/papers/icaart2024.pdf",
    abstract = "Computational argumentation has evolved as a key area in artificial intelligence, used to analyze aspects of thinking, making decisions, and conversing. As a result, it is currently employed in a variety of real-world contexts, from legal reasoning to intelligence analysis. An argumentation framework is modelled as a graph where the nodes represent arguments and the edges of the graph represent relations (i.e., supports, attacks) between nodes. In this work, we investigate the ability of neural network methods to learn a gradual bipolar argumentation semantics, which allows for both supports and attacks. We begin by calculating the acceptability degrees for graph nodes. These scores are generated using Quantitative Argumentation Debate (QuAD) argumentation semantics. We apply this approach to two benchmark datasets: Twelve Angry Men and Debate- pedia. Using this data, we train and evaluate the performance of three benchmark architectures: Multilayer Perceptron (MLP), Graph Convolution Network (GCN), and Graph Attention Network (GAT) to learn the acceptability degree scores produced by the QuAD semantics. Our results show that these neural network methods can learn bipolar gradual argumentation semantics. The models trained on GCN architecture perform better than the other two architectures underscoring the importance of modelling argumentation graphs explicitly."
}

@inproceedings{
    pyarelal2023the,
    title={The To{MCAT} Dataset},
    author={Adarsh Pyarelal and Eric Duong and Caleb Jones Shibu and Paulo Soares and Savannah Boyd and Payal Khosla and Valeria Pfeifer and Diheng Zhang and Eric S Andrews and Rick Champlin and Vincent Paul Raymond and Meghavarshini Krishnaswamy and Clayton Morrison and Emily Butler and Kobus Barnard},
    booktitle={Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
    year={2023},
    url={https://openreview.net/forum?id=ZJWQfgXQb6}
}

@inproceedings{qamar-etal-2023-speaking,
    title = "Who is Speaking? Speaker-Aware Multiparty Dialogue Act Classification",
    author = "Qamar, Ayesha  and
      Pyarelal, Adarsh  and
      Huang, Ruihong",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-emnlp.678",
    pages = "10122--10135",
    abstract = "Utterances do not occur in isolation in dialogues; it is essential to have the information of who the speaker of an utterance is to be able to recover the speaker{'}s intention with respect to the surrounding context. Beyond simply capturing speaker switches, identifying how speakers interact with each other in a dialogue is crucial to understanding conversational flow. This becomes increasingly important and simultaneously difficult to model when more than two interlocutors take part in a conversation. To overcome this challenge, we propose to explicitly add speaker awareness to each utterance representation. To that end, we use a graph neural network to model how each speaker is behaving within the local context of a conversation. The speaker representations learned this way are then used to update their respective utterance representations. We experiment with both multiparticipant and dyadic conversations on the MRDA and SwDA datasets and show the effectiveness of our approach.",
}

@inproceedings{miah-etal-2023-hierarchical,
    title = "Hierarchical Fusion for Online Multimodal Dialog Act Classification",
    author = "Miah, Md Messal Monem  and
      Pyarelal, Adarsh  and
      Huang, Ruihong",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-emnlp.505",
    pages = "7532--7545",
    abstract = "We propose a framework for online multimodal dialog act (DA) classification based on raw audio and ASR-generated transcriptions of current and past utterances. Existing multimodal DA classification approaches are limited by ineffective audio modeling and late-stage fusion. We showcase significant improvements in multimodal DA classification by integrating modalities at a more granular level and incorporating recent advancements in large language and audio models for audio feature extraction. We further investigate the effectiveness of self-attention and cross-attention mechanisms in modeling utterances and dialogs for DA classification. We achieve a substantial increase of 3 percentage points in the F1 score relative to current state-of-the-art models on two prominent DA classification datasets, MRDA and EMOTyDA.",
}

@inproceedings{cooper-etal-2023-hiding,
    title = "Hiding in Plain Sight: Tweets with Hate Speech Masked by Homoglyphs",
    author = "Cooper, Portia  and
      Surdeanu, Mihai  and
      Blanco, Eduardo",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-emnlp.192",
    doi = "10.18653/v1/2023.findings-emnlp.192",
    pages = "2922--2929",
    abstract = "To avoid detection by current NLP monitoring applications, progenitors of hate speech often replace one or more letters in offensive words with homoglyphs, visually similar Unicode characters. Harvesting real-world hate speech containing homoglyphs is challenging due to the vast replacement possibilities. We developed a character substitution scraping method and assembled the Offensive Tweets with Homoglyphs (OTH) Dataset (N=90,788) with more than 1.5 million occurrences of 1,281 non-Latin characters (emojis excluded). In an annotated sample (n=700), 40.14{\%} of the tweets were found to contain hate speech. We assessed the performance of seven transformer-based hate speech detection models and found that they performed poorly in a zero-shot setting (F1 scores between 0.04 and 0.52) but normalizing the data dramatically improved detection (F1 scores between 0.59 and 0.71). Training the models using the annotated data further boosted performance (highest micro-averaged F1 score=0.88, using five-fold cross validation). This study indicates that a dataset containing homoglyphs known and unknown to the scraping script can be collected, and that neural models can be trained to recognize camouflaged real-world hate speech.",
}

@inproceedings{kwak-et-al-nllp2023-error-analysis,
    title = "Transferring Legal Natural Language Inference Model from a US State to Another: What Makes It So Hard?",
    author = "Alice Kwak and Gaetano Forte and Derek Bambauer and Mihai Surdeanu",
    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2023",
    month = dec,
    year = "2023",
    url = "https://clulab.org/papers/nllp2023_kwak-et-al.pdf",
    abstract = "This study investigates whether a legal natural language inference (NLI) model trained on the data from one US state can be transferred to another state. We fine-tuned a pre-trained model on the task of evaluating the validity of legal will statements, once with the dataset containing the Tennessee wills and once with the dataset containing the Idaho wills. Each model’s performance on the in-domain setting and the out-of-domain setting are compared to see if the models can across the states. We found that the model trained on one US state can be mostly transferred to another state. However, it is clear that the model’s performance drops in the out-of-domain setting. The F1 scores of the Tennessee model and the Idaho model are 96.41 and 92.03 when predicting the data from the same state, but they drop to 66.32 and 81.60 when predicting the data from another state. Subsequent error analysis revealed that there are two major sources of errors. First, the model fails to recognize equivalent laws across states when there are stylistic differences between laws. Second, difference in statutory section numbering system between the states makes it difficult for the model to locate laws relevant to the cases being predicted on. This analysis provides insights on how the future NLI system can be improved. Also, our findings offer empirical support to legal experts advocating the standardization of legal documents.",
}

@inproceedings{kwak-et-al-emnlp2023-ie4wills,
    title = "Information Extraction from Legal Wills: How Well Does GPT-4 Do?",
    author = "Alice Kwak and Cheonkam Jeong and Gaetano Forte and Derek Bambauer and Clayton Morrison and Mihai Surdeanu",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    url = "https://clulab.org/papers/emnlp2023_kwak-et-al.pdf",
    abstract = "This work presents a manually annotated dataset for Information Extraction (IE) from legal wills, and relevant in-context learning experiments on the dataset. The dataset consists of entities, binary relations between the entities (e.g., relations between testator and beneficiary), and n-ary events (e.g., bequest) extracted from 45 legal wills from two US states. This dataset can serve as a foundation for downstream tasks in the legal domain. Another use case of this dataset is evaluating the performance of large language models (LLMs) on this IE task. We evaluated GPT-4 with our dataset to investigate its ability to extract information from legal wills. Our evaluation result demonstrates that the model is capable of handling the task reasonably well. When given instructions and examples as a prompt, GPT-4 shows decent performance for both entity extraction and relation extraction tasks. Nevertheless, the evaluation result also reveals that the model is not perfect. We observed inconsistent outputs (given a prompt) as well as prompt over-generalization.",
}

@inproceedings{rahimi-surdeanu-2023-improving,
    title = "Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates",
    author = "Rahimi, Mahdi  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.repl4nlp-1.16",
    pages = "187--195",
    abstract = "While fully supervised relation classification (RC) models perform well on large-scale datasets, their performance drops drastically in low-resource settings. As generating annotated examples are expensive, recent zero-shot methods have been proposed that reformulate RC into other NLP tasks for which supervision exists such as textual entailment. However, these methods rely on templates that are manually created which is costly and requires domain expertise. In this paper, we present a novel strategy for template generation for relation classification, which is based on adapting Harris{'} distributional similarity principle to templates encoded using contextualized representations. Further, we perform empirical evaluation of different strategies for combining the automatically acquired templates with manual templates. The experimental results on TACRED show that our approach not only performs better than the zero-shot RC methods that only use manual templates, but also that it achieves state-of-the-art performance for zero-shot TACRED at 64.3 F1 score.",
}

@inproceedings{george-surdeanu-2023-sexually,
    title = "It{'}s not Sexually Suggestive; It{'}s Educative | Separating Sex Education from Suggestive Content on {T}ik{T}ok Videos",
    author = "George, Enfa  and
      Surdeanu, Mihai",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-acl.365",
    pages = "5904--5915",
    abstract = "We introduce SexTok, a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator{'}s point of view), sex-educational content, or neither. Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok. Children{'}s exposure to sexually suggestive videos has been shown to have adversarial effects on their development (Collins et al. 2017). Meanwhile, virtual sex education, especially on subjects that are more relevant to the LGBTQIA+ community, is very valuable (Mitchell et al. 2014). The platform{'}s current system removes/punishes some of both types of videos, even though they serve different purposes. Our dataset contains video URLs, and it is also audio transcribed. To validate its importance, we explore two transformer-based models for classifying the videos. Our preliminary results suggest that the task of distinguishing between these types of videos is learnable but challenging. These experiments suggest that this dataset is meaningful and invites further study on the subject.",
}

@inproceedings{Vacareanu2022PatternRankJR,
    title = {PatternRank: Jointly Ranking Patterns and Extractions for Relation Extraction Using Graph-Based Algorithms},
    author = {Robert Vacareanu and Dane Bell and Mihai Surdeanu},
    booktitle = {PANDL},
    abstract="{In this paper we revisit the direction of using lexico-syntactic patterns for relation extraction instead of today's ubiquitous neural classifiers. We propose a semi-supervised graph-based algorithm for pattern acquisition that scores patterns and the relations they extract jointly, using a variant of PageRank. We insert light supervision in the form of seed patterns or relations, and model it with several custom teleportation probabilities that bias random-walk scores of patterns/relations based on their proximity to correct information. We evaluate our approach on Few-Shot TACRED, and show that our method outperforms (or performs competitively with) more expensive and opaque deep neural networks. Lastly, we thoroughly compare our proposed approach with the seminal RlogF pattern acquisition algorithm of, showing that it outperforms it for all the hyper parameters tested, in all settings. }",
    url = {https://aclanthology.org/2022.pandl-1.1.pdf},
    year = {2022}
}

@article{Vacareanu2022AHI,
    title = {A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction},
    author = {Robert Vacareanu and George Caique Gouveia Barbosa and Enrique Noriega-Atala and Gus Hahn-Powell and Rebecca Sharp and Marco Antonio Valenzuela-Escarcega and Mihai Surdeanu},
    journal = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations},
    abstract = "{We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis.Users of our system can specify their requirements through the use of examples,which are collected with a search interface.The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system.Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns.Our code, demo, and documentation is available at https://clulab.github.io/odinsynth.}",
    url = {https://aclanthology.org/2022.naacl-demo.8.pdf},
    year = {2022}
}

@inproceedings{nitschke-etal-2022-rule,
    title = "Rule Based Event Extraction for Artificial Social Intelligence",
    author = "Nitschke, Remo  and
      Wang, Yuwei  and
      Chen, Chen  and
      Pyarelal, Adarsh  and
      Sharp, Rebecca",
    booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Conference on Computational Linguistics",
    url = "https://aclanthology.org/2022.pandl-1.9",
    pages = "71--84",
    abstract = "Natural language (as opposed to structured communication modes
        such as Morse code) is by far the most common mode of communication
        between humans, and can thus provide significant insight into both
        individual mental states and interpersonal dynamics. As part of
        DARPA{'}s Artificial Social Intelligence for Successful Teams (ASIST)
        program, we are developing an AI agent team member that constructs and
        maintains models of their human teammates and provides appropriate
        task-relevant advice to improve team processes and mission performance.
        One of the key components of this agent is a module that uses a
        rule-based approach to extract task-relevant events from natural
        language utterances in real time, and publish them for consumption by
        downstream components. In this case study, we evaluate the performance
        of our rule-based event extraction system on a recently conducted ASIST
        experiment consisting of a simulated urban search and rescue mission in
        Minecraft. We compare the performance of our approach with that of a
        zero-shot neural classifier, and find that our approach outperforms the
        classifier for all event types, even when the classifier is used in an
        oracle setting where it knows how many events should be extracted from
        each utterance.",
}

@inproceedings{zupon2020capsnet,
  title={An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios},
  author={Zupon, Andrew and Rafique, Faiz and Surdeanu, Mihai},
  booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP},
  url={http://clulab.org/papers/insights2020-capsnet.pdf},
  year={2020}
}

@inproceedings{liang2020can,
  title={Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?},
  author={Liang, Zhengzhong and Surdeanu, Mihai},
  booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP},
  url={http://clulab.org/papers/emnlp2020-can.pdf},
  year={2020}
}

@article{van2020covid,
  title={The Language of Food during the Pandemic: Hints about the Dietary Effects of Covid-19},
  author={Hoang Van and Ahmad Musa and Mihai Surdeanu and Stephen Kobourov},
  journal={arXiv preprint arXiv:2010.07466},
  url={https://arxiv.org/abs/2010.07466},
  year={2020}
}

@article{liang2020using,
  title={Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering},
  author={Liang, Zhengzhong and Zhao, Yiyun and Surdeanu, Mihai},
  journal={arXiv preprint arXiv:2009.10791},
  url = "https://arxiv.org/abs/2009.10791",
  year={2020}
}

@InProceedings{jansen-EtAl:2016:COLING,
  author    = {Jansen, Peter  and  Balasubramanian, Niranjan  and  Surdeanu, Mihai  and  Clark, Peter},
  title     = {What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {2956-2965},
  url       = {http://aclweb.org/anthology/C16-1278},
  url_Data  = {http://allenai.org/data.html},
}
@inproceedings{valenzuela2015identifying,
  title={Identifying meaningful citations},
  author={Valenzuela, Marco and Ha, Vu and Etzioni, Oren},
  booktitle={Proceedings of the "Scholarly Big Data: AI Perspectives, Challenges, and Ideas" Workshop at the Twenty-Ninth AAAI Conference on Artificial Intelligence},
  year={2015},
  url={http://ai2-website.s3.amazonaws.com/publications/ValenzuelaHaMeaningfulCitations.pdf}
}
@inproceedings{Jansen:14,
	year = {2014},
	author = {Jansen, Peter and Surdeanu, Mihai and Clark, Peter},
	booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)},
	title = {Discourse Complements Lexical Semantics for Non-factoid Answer Reranking},
  url = {http://clulab.org/papers/acl2014.pdf},
  url_Code_And_Data = {http://nlp.sista.arizona.edu/releases/acl2014/},
  url_Slides = {http://nlp.sista.arizona.edu/releases/acl2014/},
}
@inproceedings{Manning:14,
	year = {2014},
	author = {Manning, Christopher D. and Surdeanu, Mihai and Bauer, John and Finkel, Jenny and Bethard, Steven J. and McClosky, David},
	booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)},
	title = {The Stanford CoreNLP Natural Language Processing Toolkit},
  url = {http://clulab.org/papers/acl2014-corenlp.pdf},
  url_Code = {http://nlp.stanford.edu/software/corenlp.shtml},
}
@InProceedings{Valenzuela:15,
  author    = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell and Thomas Hicks and Mihai Surdeanu},
  title     = {A Domain-independent Rule-based Framework for Event Extraction},
  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Assian Federation of Natural Language Processing: Software Demonstrations (ACL-IJCNLP)},
  year      = {2015},
  url      = {http://clulab.org/papers/acl2015.pdf},
  url_Code  = {https://github.com/sistanlp/processors},
}
@inproceedings{Fried:14,
	year = {2014},
	author = {Fried, Daniel and Surdeanu, Mihai and Kobourov, Stephen and Hingle, Melanie and Bell, Dane},
	booktitle = {Proceedings of the 2014 IEEE International Conference on Big Data},
	title = {Analyzing the Language of Food on Social Media},
  url = {http://clulab.org/papers/bigdata2014.pdf},
  url_Supplmental_Material = {http://arxiv.org/abs/1409.2195},
  url_Demo = {https://sites.google.com/site/twitter4food/},
}
@InProceedings{Valenzuela:16b,
  author    = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell and Dane Bell and Mihai Surdeanu},
  title     = {SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction},
  booktitle = {Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016)},
  year      = {2016},
  url       = {https://arxiv.org/abs/1606.09604},
}
@InProceedings{HahnPowell:16,
  author    = {Gustave Hahn-Powell and Dane Bell and Valenzuela-Escarcega, Marco A. and Mihai Surdeanu},
  title     = {This before That: Causal Precedence in the Biomedical Domain},
  booktitle = {Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016)},
  year      = {2016},
  url       = {https://arxiv.org/abs/1606.08089},
  note         = {Latest results can be found at {https://repository.arizona.edu/handle/10150/630562}}
}
@Article{Zapirain:13,
  author    = {Benat Zapirain and Eneko Agirre and Lluis Marquez and Mihai Surdeanu},
  title     = {Selectional Preferences for Semantic Role Classification},
  journal = {Computational Linguistics},
  volume = {39},
  number = {3},
  year      = {2013},
  url = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00145},
}
@Article{Lee:13,
  author    = {Heeyoung Lee and Angel Chang and Yves Peirsman and Nathanael Chambers and Mihai Surdeanu and Dan Jurafsky},
  title     = {Deterministic coreference resolution based on entity-centric, precision-ranked rules},
  journal = {Computational Linguistics},
  volume = {39},
  number = {4},
  year      = {2013},
  url = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00152},
}
@inproceedings{Sharp2016,
	year = {2016},
	author = {Sharp, Rebecca and Mihai Surdeanu and Peter Jansen and Peter Clark and Michael Hammond},
	booktitle = {Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
	title = {Creating Causal Embeddings for Question Answering with Minimal Supervision},
  url = {http://arxiv.org/abs/1609.08097},
  url_Data_and_Code = {http://clulab.org/data/emnlp2016-causal/},
}
@inproceedings{surdeanu2013-icail,
	year = {2013},
	author = {Mihai Surdeanu and Sara Jeruss},
	booktitle = {Proceedings of the XIV International Conference on Artificial Intelligence and Law (ICAIL)},
	title = {Identifying Patent Monetization Entities},
  url = {http://clulab.org/papers/icail2013.pdf},
}
@inproceedings{Surdeanu:13,
	year = {2013},
	author = {Surdeanu, Mihai},
	booktitle = {Proceedings of the TAC-KBP 2013 Workshop},
	title = {Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling and Temporal Slot Filling},
  url = {http://clulab.org/papers/kbp2013.pdf},
  url_Slides_SF = {http://clulab.org/papers/kbp2013_sf.pdf},
  url_Slides_TSF = {http://clulab.org/papers/kbp2013_tsf.pdf},
}
@inproceedings{SurdeanuHeng:14,
	year = {2014},
	author = {Surdeanu, Mihai and Heng, Ji},
	booktitle = {Proceedings of the TAC-KBP 2014 Workshop},
	title = {Overview of the English Slot Filling Track at the TAC2014 Knowledge Base Population Evaluation},
  url = {http://clulab.org/papers/kbp2014_draft.pdf},
}
@inproceedings{Reschke:14,
	year = {2014},
	author = {Reschke, Kevin and Jankowiak, Martin and Surdeanu, Mihai and Manning, Christopher D. and Jurafsky, Dan},
	booktitle = {Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC)},
	title = {Event Extraction Using Distant Supervision},
  url = {http://clulab.org/papers/lrec2014_ds.pdf},
  url_Data = {http://nlp.stanford.edu/projects/dist-sup-event-extraction.shtml},
  url_Slides = {http://clulab.org/papers/lrec2014_ds_slides.pdf}
}
@inproceedings{Lee:14,
	year = {2014},
	author = {Lee, Heeyoung and MacCartney, Bill and Surdeanu, Mihai and Jurafsky, Dan},
	booktitle = {Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC)},
	title = {On the Importance of Text Analysis for Stock Price Prediction},
  url = {http://clulab.org/papers/lrec2014_stocks.pdf},
  url_Data = {http://nlp.stanford.edu/pubs/stock-event.html},
  url_Slides = {http://clulab.org/papers/lrec2014_stocks_slides.pdf},
}
@InProceedings{Bell:16,
  author    = {Bell, Dane and Gustave Hahn-Powell and Marco A. Valenzuela-Escarcega and Gustave Hahn-Powell  and Mihai Surdeanu},
  title     = {An Investigation of Coreference Phenomena in the Biomedical Domain},
  booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},
  year      = {2016},
  url       = {http://clulab.org/papers/lrec2016-coref.pdf},
  url_Code  = {https://github.com/clulab/reach},
}
@InProceedings{Valenzuela:16,
  author    = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell  and Mihai Surdeanu},
  title     = {Odin's Runes: A Rule Language for Information Extraction},
  booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},
  year      = {2016},
  url       = {http://surdeanu.info/mihai/papers/lrec2016-odin.pdf},
  url_Code  = {https://github.com/sistanlp/processors},
}
@InProceedings{Bell:16b,
  author    = {Bell, Dane and Daniel Fried and Luwen Huangfu and Mihai Surdeanu and Stephen Kobourov},
  title     = {Towards Using Social Media to Identify Individuals at Risk for Preventable Chronic Illness},
  booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},
  year      = {2016},
  url       = {http://clulab.org/papers/lrec2016-t4f.pdf},
  url_Code  = {https://github.com/clulab/twitter4food},
}
@InProceedings{Surdeanu:15,
  author    = {Surdeanu, Mihai and Thomas Hicks and Marco A. Valenzuela-Escarcega},
  title     = {Two Practical Rhetorical Structure Theory Parsers},
  booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations},
  year      = {2015},
  url       = {http://clulab.org/papers/naacl2015-discourse.pdf},
  url_Code  = {https://github.com/sistanlp/processors},
}
@InProceedings{Intxaurrondo:15,
  author    = {Intxaurrondo, Ander and Eneko Agirre and Oier Lopez de Lacalle and Mihai Surdeanu},
  title     = {Diamonds in the Rough: Event Extraction from Imperfect Microblog Data},
  booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT)},
  year      = {2015},
  url       = {http://clulab.org/papers/naacl2015-ee.pdf},
  url_Data  = {http://ixa.eus/Ixa/Argitalpenak/Artikuluak/1425465524/publikoak/earthquake-kb-dataset.zip},
}
@InProceedings{Sharp:15,
  author    = {Sharp, Rebecca and Peter Jansen and Mihai Surdeanu and Peter Clark},
  title     = {Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering},
  booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT)},
  year      = {2015},
  url       = {http://clulab.org/papers/naacl2015-qa.pdf},
  url_Data_and_Some_Code = {http://surdeanu.cs.arizona.edu/mihai/papers/straw2gold.zip},
}
@inproceedings{intxaurrondo13,
	year = {2013},
	author = {Ander Intxaurrondo and Mihai Surdeanu and Oier Lopez de Lacalle and Eneko Agirre},
	booktitle = {Proceedings of the 29th "Congreso de la Sociedad Espa{\~{n}}ola para el Procesamiento del Lenguaje Natural" (SEPLN 2013)},
	title = {Removing Noisy Mentions for Distant Supervision},
  url = {http://clulab.org/papers/sepln13.pdf},
}
@inproceedings{Tran:14,
	year = {2014},
	author = {Tran, Anh and Surdeanu, Mihai and Cohen, Paul},
	booktitle = {Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM)},
	title = {Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge},
  url = {http://clulab.org/papers/starsem2014.pdf},
  url_Slides = {http://clulab.org/papers/starsem2014_slides.pdf},
}
@article{Fried:2015,
        author = {Daniel Fried and Peter Jansen and Gustave Hahn-Powell and Mihai
Surdeanu and Peter Clark},
        title = {Higher-order Lexical Semantic Models for Non-factoid Answer
Reranking},
        journal = {Transactions of the Association for Computational Linguistics},
        volume = {3},
        year = {2015},
        keywords = {},
        abstract = {Lexical semantic models provide robust performance for question
answering, but, in general, can only capitalize on direct evidence seen
during training. For example, monolingual alignment models acquire term
alignment probabilities from semi-structured data such as question-answer
pairs; neural network language models learn term embeddings from
unstructured text. All this knowledge is then used to estimate the semantic
similarity between question and answer candidates.  We introduce a
higher-order formalism that allows all these lexical semantic models to
chain direct evidence to construct indirect associations between question
and answer texts, by casting the task as the traversal of graphs that encode
direct term associations.  Using a corpus of 10,000 questions from Yahoo!
Answers, we experimentally demonstrate that higher-order methods are broadly
applicable to alignment and language models, across both word and syntactic
representations. We show that an important criterion for success is
controlling for the semantic drift that accumulates during graph traversal.
All in all, the proposed higher-order approach improves five out of the six
lexical semantic models investigated, with relative gains of up to +13\%
over their first-order variants. },
        issn = {2307-387X},
        url =
{https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/550},
        pages = {197-210}
}
@inproceedings{Forbes:13,
	year = {2013},
	author = {Angus Forbes and Mihai Surdeanu and Peter Jansen and Jane Carrington},
	booktitle = {Proceedings of the 3rd IEEE Workshop on Interactive Visual Text Analytics},
	title = {Transmitting Narrative: An Interactive Shift-Summarization Tool for Improving Nurse Communication},
  url = {http://clulab.org/papers/textvis2013.pdf},
}
@article{valenzuela2015description,
  title={Description of the odin event extraction framework and rule language},
  author={Valenzuela-Escarcega, Marco A and Hahn-Powell, Gus and Surdeanu, Mihai},
  journal={arXiv preprint arXiv:1509.07513},
  year={2015},
  url={https://arxiv.org/pdf/1509.07513},
}
@InProceedings{Colin:NAACLHLT2013,
title={Bayesian modeling of scenes and captions},
author={Colin R. Dawson, Luca Del Pero, Clayton T. Morrison, Mihai Surdeanu, Gustave Hahn-Powell, Zachary Chapman and Kobus Barnard},
year={2013},
booktitle={Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2013), Workshop on Vision and Language (WVL)},
url_Slides={http://surdeanu.info/mihai/papers/wvl2013_slides.pdf},
}
@inproceedings{sharp2017tell,
  title={Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification},
  author={Sharp, Rebecca and Surdeanu, Mihai and Jansen, Peter and Valenzuela-Escarcega, Marco A and Clark, Peter and Hammond, Michael},
  booktitle={Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
  pages={69-79},
  year={2017},
  url={http://www.aclweb.org/anthology/K17-1009}
}
@article{jansen2017framing,
  title={Framing QA as Building and Ranking Intersentence Answer Justifications},
  author={Jansen, Peter and Sharp, Rebecca and Surdeanu, Mihai and Clark, Peter},
  journal={Computational Linguistics},
  year={2017},
  publisher={MIT Press},
  url={http://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00287}
}
@inproceedings{noriega2017learning,
  title={Learning what to read: Focused machine reading},
  author={Noriega-Atala, Enrique and Valenzuela-Escarcega, Marco A and Morrison, Clayton and Surdeanu, Mihai},
  booktitle={Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  pages={2895-2900},
  year={2017},
  url={https://arxiv.org/pdf/1709.00149.pdf}
}
@article{lee2017scaffolding,
  title={A scaffolding approach to coreference resolution integrating statistical and rule-based models},
  author={Lee, Heeyoung and Surdeanu, Mihai and Jurafsky, Dan},
  journal={Natural Language Engineering},
  pages={1-30},
  year={2017},
  publisher={Cambridge University Press},
  url={https://www.cambridge.org/core/services/aop-cambridge-core/content/view/042D0D6C6E125EFB939E0F2C2E63152B/S1351324917000109a.pdf/div-class-title-a-scaffolding-approach-to-coreference-resolution-integrating-statistical-and-rule-based-models-div.pdf}
}
@article{hahn2017swanson,
  title={Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph},
  author={Hahn-Powell, Gus and Valenzuela-Escarcega, Marco A and Surdeanu, Mihai},
  journal={Proceedings of ACL 2017, System Demonstrations},
  pages={103-108},
  year={2017},
  url={http://www.aclweb.org/anthology/P17-4018}
}
@inproceedings{enrique2017focused,
  title={Focused Reading: Reinforcement Learning for What Documents to Read},
  author={Enrique Noriega-Atala and Marco A. Valenzuela-Escarcega and Clayton T. Morrison and Mihai Surdeanu},
  booktitle={Proceedings of the Interactive Machine Learning and Semantic Information Retrieval Workshop at ICML, 2017},
  year={2017},
  url={http://clulab.org/papers/focusedreading2017.pdf}
}
@inproceedings{biocreative6,
title={{Large-scale automated reading with Reach discovers new cancer driving mechanisms}},
author={Valenzuela-Escarcega, Marco A. and Ozgun Babur and Gus Hahn-Powell and Dane Bell and Thomas Hicks and Enrique Noriega-Atala and Xia Wang and Mihai Surdeanu and Emek Demir and Clayton T. Morrison},
pages={201-203},
year={2017},
booktitle={Proceedings of the Sixth BioCreative Challenge Evaluation Workshop},
url={http://clulab.org/papers/biocreative6.pdf}
}
@article{Rains:20182,
        author = {Stephen A. Rains and Melanie D. Hingle and Mihai Surdeanu and Dane Bell and Stephen Kobourov},
        title = {Effects of Message Framing on Diabetes Screening Attitudes and Behavior},
        journal = {Manuscript in preparation},
        year = {2018},
        url = {http://clulab.org/papers/DiabetesMessageFramingStudyBriefReport.pdf}
}
@inproceedings{lrec2018,
  title={Grounding Gradable Adjectives through Crowdsourcing},
  author={Sharp, Rebecca and Paul, Mithun and Nagesh, Ajay and Bell, Dane and Surdeanu, Mihai},
  booktitle={LREC 2018},
  year={2018},
  url={http://clulab.org/papers/GroundingGradableAdjectivesthroughCrowdsourcing.pdf}
}
@Article{Rains:2018,
  author    = {Stephen A. Rains and Melanie D. Hingle and Mihai Surdeanu and Dane Bell and Stephen Kobourov},
  title     = {A Test of The Risk Perception Attitude Framework as a Message Tailoring Strategy to Promote Diabetes Screening},
  journal = {Health Communication},
  url = {http://clulab.org/papers/RainsHingleSurdeanuetalHC.pdf},
  url_odi = {https://doi.org/10.1080/10410236.2018.1431024},
  year = {2018}
}
@InProceedings{jansen2018worldtree,
    author = {Peter Jansen and Elizabeth Wainwright and Steven Marmorstein and Clayton T. Morrison},
    title = {WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference},
    booktitle = {Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC)},
    year = {2018},
    url = {http://cognitiveai.org/wp-content/uploads/2018/02/jansen_et_al_lrec2018_worldtree_computable_explanation_corpus_8pg_cameraready.pdf},
    url_code = {http://cognitiveai.org/explanationbank/}
}
@inproceedings{jansen:akbc2017,
 author = {Peter Jansen},
 title = {A Study of Automatically Acquiring Explanatory Inference Patterns from Corpora of Explanations: Lessons from Elementary Science Exams},
 booktitle = {Proceedings of the 2017 Workshop on Automated Knowledge Base Construction},
 series = {AKBC'17},
 year = {2017},
 url = {http://cognitiveai.org/wp-content/uploads/2017/11/jansen_akbc2017_automatically_acquiring_explanatory_inference_patterns_from_corpora_of_explanations.pdf},
 url_data = {http://cognitiveai.org/explanationbank/}
}
@InProceedings{heeyoung2018ecir,
    author = {Heeyoung Kwon and Harsh Trivedi and Peter Jansen and Mihai Surdeanu and Niranjan Balasubramanian},
    title = {Controlling Information Aggregation for Complex Question Answering},
    booktitle = {Proceedings of the 40th European Conference on Information Retrieval (ECIR)},
    year = {2018},
    url = {http://clulab.org/papers/ecir2018.pdf}
}
@inproceedings{TAG-2018,
    author = {Angus G. Forbes and Kristine Lee and Gus Hahn-Powell and Marco A. Valenzuela-Escarcega and Mihai Surdeanu},
    title = {Text Annotation Graphs: Annotating Complex Natural Language Phenomena},
    booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC'18)},
    year = {2018},
    month = {May},
    address = {Miyazaki, Japan},
    publisher = {European Language Resources Association (ELRA)},
    url_code = {https://github.com/CreativeCodingLab/TextAnnotationGraphs},
    url = {https://arxiv.org/pdf/1711.00529.pdf}
 }
@inproceedings{DBLP:conf/naacl/ANMS18,
  author    = {Ajay Nagesh and
               Mihai Surdeanu},
  title     = {Keep your bearings: Lightly-supervised Information Extraction with Ladder Networks that avoids Semantic Drift},
  booktitle = {{NAACL} {HLT} 2018, The 16th Annual Conference of the North American Chapter
               of the Association for Computational Linguistics: Human Language Technologies,
               New Orleans, Louisiana, USA, Jun 1 - June 6, 2018},
  year      = {2018},
  url = {http://clulab.org/papers/naaclhlt2018.pdf}
}
@inproceedings{whitespaces-identification2018,
  title={Scientific Discovery as Link Prediction in Influence and Citation Graphs},
  author={Fan Luo and
      	Marco A. Valenzuela-Escarcega and
        Gus Hahn-Powell and
        Mihai Surdeanu},
  booktitle = {TextGraphs: 12th Workshop on Graph-Based Natural Language Processing},
  year={2018},
  abstract = {We introduce a machine learning approach for the identification of ``white spaces'' in scientific knowledge. Our approach addresses this task as link prediction over a graph that contains over 2M influence statements such as ``CTCF activates FOXA1'', which were automatically extracted using open-domain machine reading. We model this prediction task using graph-based features extracted from the above influence graph, as well as from a citation graph that captures scientific communities. We evaluated the proposed approach through backtesting. Although the data is heavily unbalanced (50 times more negative examples than positives), our approach predicts which influence links will be discovered in the ``near future'' with a F1 score of 27 points, and a mean average precision of 68\%. },
  organization={NAACL},
  url_Slides={http://clulab.org/papers/TextGraphs.pdf},
  url={http://clulab.org/papers/ScientificDiscoveryasLinkPredictioninInfluenceandCitationGraphs.pdf}
}
@inproceedings{vikasy_ARC_2018,
  title={Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge},
  author={Yadav, Vikas and Sharp, Rebecca and Surdeanu, Mihai},
  booktitle = "Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)",
  year={2018},
  url = {https://arxiv.org/pdf/1807.01836.pdf}
}
@article{vikasy_ARC_2018,
  title={Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge},
  author={Yadav, Vikas and Sharp, Rebecca and Surdeanu, Mihai},
  year={2018},
  url = {https://arxiv.org/pdf/1807.01836.pdf}
}
@inproceedings{lrec2018,
  title={Lightly-supervised Representation Learning with Global Interpretability},
  author={Valenzuela-Escarcega, Marco A  and Nagesh, Ajay and Surdeanu, Mihai},
  booktitle={arXiv},
  year={2018},
  url={https://arxiv.org/abs/1805.11545/}
}
@InProceedings{SHARP18.977,
  author = {Rebecca Sharp and Mithun Paul and Ajay Nagesh and Dane Bell and Mihai Surdeanu},
  title = {Grounding gradable adjectives through crowdsourcing},
  booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year = {2018},
  month = {May},
  date = {7-12},
  location = {Miyazaki, Japan},
  editor = {Nicoletta Calzolari and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and H\'{e}l\`{e}ne Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
  publisher = {European Language Resources Association (ELRA)},
  address = {Paris, France},
  isbn = {979-10-95546-00-9},
  language = {english},
  url = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/977.pdf}
}
@InProceedings{bell2018detecting,
  title	    = {Detecting diabetes risk from social media activity},
  author    = {Bell, Dane and Laparra, Egoitz and Kousik, Aditya and Ishihara, Terron and Surdeanu, Mihai and Kobourov, Stephen},
  booktitle = {Ninth International Workshop on Health Text Mining and Information Analysis (LOUHI)},
  year      = {2018},
  url = {http://clulab.org/papers/louhi2018-t2dmrisk.pdf},
  url_Slides = {http://clulab.org/papers/louhi2018-emnlp.pptx}
}
@Article{Zhou:2018,
  author    = {Jun Zhou and Dane Bell and Sabina Nusrat and Melanie D.\ Hingle and Mihai Surdeanu and Stephen Kobourov},
  title     = {Calorie estimation from pictures of food: Crowdsourcing study},
  journal = {Interactive Journal of Medical Research (IJMR)},
  url = {http://clulab.org/papers/Zhou2018.pdf},
  doi = {10.2196/ijmr.9359},
  year = {2018}
}
@InProceedings{C18-1196,
  author = 	"Nagesh, Ajay
		and Surdeanu, Mihai",
  title = 	"An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification",
  booktitle = 	"Proceedings of the 27th International Conference on Computational Linguistics",
  year = 	"2018",
  publisher = 	"Association for Computational Linguistics",
  pages = 	"2312-2324",
  location = 	"Santa Fe, New Mexico, USA",
  url = 	"http://aclweb.org/anthology/C18-1196"
}
@Article{ValenzuelaEscarcega2018LargescaleAR,
  title     = {Large-scale Automated Machine Reading Discovers New
Cancer Driving Mechanisms},
  author  = {Valenzuela{-}Escarcega, Marco A. and Ozgun Babur and Gus Hahn-Powell and Dane Bell and Thomas Hicks and Enrique Noriega-Atala and Xia Wang and Mihai Surdeanu and Emek Demir and Clayton T. Morrison},
  journal = {Database: The Journal of Biological Databases and Curation},
  url = {http://clulab.org/papers/escarcega2018.pdf},
  doi = {10.1093/database/bay098},
  year = {2018}
}
@inproceedings{berger2018emboot,
  title={Visual Supervision in Bootstrapped Information Extraction},
  author={Berger, Matthew and Nagesh, Ajay and Levine, Joshua A. and Surdeanu, Mihai and Zhang, Hao Helen},
  booktitle={Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2018},
  url={http://clulab.org/papers/emnlp2018.pdf}
}
@InProceedings{Ebrahimi2018isi,
    author = {Mohammadreza Ebrahimi and Mihai Surdeanu and Sagar Samtani and Hsinchun Chen},
    title = {Detecting Cyber Threats in Non-English Dark Net Markets: A Cross-Lingual Transfer Learning Approach},
    booktitle = {Proceedings of the IEEE Intelligence and Security Informatics Conference (ISI)},
    year = {2018},
    note = {This paper won the Best Paper Runner-up Award.},
    url = {http://clulab.org/papers/isi2018.pdf}
}
@inproceedings{barbosa2019,
    title={Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text},
    author={Barbosa, George C.G. and Wong, Zechy and Hahn-Powell, Gus and Bell, Dane and Sharp, Rebecca and Valenzuela-Escarcega, Marco A. and Surdeanu, Mihai},
    booktitle={Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations},
    year={2019},
    note={This paper received the Best System Demonstration award},
    url={http://clulab.org/papers/NAACL2019_1.pdf}
}
@INPROCEEDINGS {polarity2019,
    author    = "Enrique Noriega-Atala and Zhengzhong Liang and John A. Bachman and Clayton T. Morrison and Mihai Surdeanu",
    title     = "Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods",
    booktitle = "Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications",
    organization={NAACL-HLT},
    year      = "2019",
    url = {http://clulab.org/papers/polarity19.pdf}
}
@inproceedings{fan2019MTre,
title={Semi-Supervised Teacher-Student Architecture for Relation Extraction},
author={Fan Luo and
Ajay Nagesh and
Rebecca Sharp and
Mihai Surdeanu},
booktitle = {Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing},
year={2019},
organization={NAACL-HLT},
url={http://clulab.org/papers/meanteacherre19.pdf}
}
@INPROCEEDINGS {naaclhlt2019-emboot,
    author       = "Andrew Zupon and Maria Alexeeva and Marco A. Valenzuela-Escarcega and Ajay Nagesh and Mihai Surdeanu",
    title        = "Lightly Supervised Representation Learning with Global Interpretability",
    booktitle    = "Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing",
    year         = "2019",
    organization = "NAACL-HLT",
    url = {http://clulab.org/papers/naaclhlt2019-emboot.pdf}
}
@phdthesis{ghpdiss2018,
        author = {Gus Hahn-Powell},
        publisher = {The University of Arizona},
        year = {2018},
        title = {Machine Reading for Scientific Discovery},
        url = {https://repository.arizona.edu/handle/10150/630562}
}
@InProceedings{van2019language,
  title	    = {What does the language of foods say about us?},
  author    = {Van, Hoang and Musa, Ahmad and Chen, Hang and Surdeanu, Mihai and Kobourov, Stephen},
  booktitle = {Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI)},
  year      = {2019},
  url = {http://clulab.org/papers/louhi2019.pdf},
  url_Slides = {http://clulab.org/papers/louhi2019.pptx}
}
@inproceedings{suntwal-etal-2019-importance,
    title = "On the Importance of Delexicalization for Fact Verification",
    author = "Suntwal, Sandeep  and
      Paul, Mithun  and
      Sharp, Rebecca  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D19-1340",
    doi = "10.18653/v1/D19-1340",
    pages = "3413-3418",
}
@InProceedings{vacareanu2020parsing,
    author = {Robert Vacareanu and George C. G. Barbosa and Marco A. Valenzuela-Escarcega and Mihai Surdeanu},
    title = {Parsing as Tagging},
    booktitle = {Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC)},
    year = {2020},
    url = {http://clulab.org/papers/pat.pdf}
}
@inproceedings{zheng-tang-2019-edin,
    title = "Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder",
    author = "Tang, Zheng and Hahn-Powell, Gustave and Surdeanu, Mihai",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
    month = jul,
    year = "2020",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "http://clulab.org/papers/aclsrw2020-edin.pdf"
}
@inproceedings{vacareanu2020mwe,
  title={An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification},
  author={Robert Vacareanu and Marco A. Valenzuela-Escarcega and Rebecca Sharp and Mihai Surdeanu},
  booktitle={The 28th International Conference on Computational Linguistics in Barcelona (COLING 2020)},
  url={http://clulab.org/papers/coling2020-mwe.pdf},
  year={2020}
}
@inproceedings{mithun2020modeldis,
  title={Data and Model Distillation as a Solution for Domain-transferable Fact Verification},
  author={Mithun, Mitch and Suntwal, Sandeep and Surdeanu, Mihai},
  booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  url={http://clulab.org/papers/knowledge_disillation.pdf},
  year={2021}
}
@inproceedings{liang2021using,
  title={Using the Hammer Only on Nails: A Hybrid Method for Representation-based Evidence Retrieval for Question Answering},
  author={Liang, Zhengzhong and Zhao, Yiyun and Surdeanu, Mihai},
  booktitle={Proceedings of 43rd European Conference on IR Research, ECIR 2021},
  url={http://clulab.org/papers/ecir2021-hybrid.pdf},
  year={2021}
}
@inproceedings{zheng-tang-2021-edin,
    title = "Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractor with an Explanation Decoder",
    author = "Tang, Zheng and Surdeanu, Mihai",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: TrustNLP Workshop",
    year = "2021",
    url = "http://clulab.org/papers/trustNLP2021_edin.pdf"
}
@inproceedings{culnan-etal-2021-ire,
    title = "Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection",
    author = "Culnan, John  and
      Park, Seongjin  and
      Krishnaswamy, Meghavarshini  and
      Sharp, Rebecca",
    booktitle = "Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
    month = apr,
    year = "2021",
    url = "https://www.aclweb.org/anthology/2021.wassa-1.26",
    pages = "250--256"
}
@article{Van2021CheapAG,
  title={Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading},
  author={Hoang Van and Vikas Yadav and M. Surdeanu},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.04134},
  url={https://arxiv.org/pdf/2106.04134.pdf}
}
@inproceedings{mithun2021students,
  title={Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification},
  author={Mithun, Mitch Paul and Suntwal, Sandeep and Surdeanu, Mihai},
  booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
  pages={6968--6973},
  year={2021},
  url={https://aclanthology.org/2021.emnlp-main.558.pdf}
}
@inproceedings{van-etal-2021-may-help,
    title = "How May {I} Help You? Using Neural Text Simplification to Improve Downstream {NLP} Tasks",
    author = "Van, Hoang  and
      Tang, Zheng  and
      Surdeanu, Mihai",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-emnlp.343",
    pages = "4074--4080",
    abstract = "The general goal of text simplification (TS) is to reduce text complexity for human consumption. In this paper, we investigate another potential use of neural TS: assisting machines performing natural language processing (NLP) tasks. We evaluate the use of neural TS in two ways: simplifying input texts at prediction time and augmenting data to provide machines with additional information during training. We demonstrate that the latter scenario provides positive effects on machine performance on two separate datasets. In particular, the latter use of TS improves the performances of LSTM (1.82{--}1.98{\%}) and SpanBERT (0.7{--}1.3{\%}) extractors on TACRED, a complex, large-scale, real-world relation extraction task. Further, the same setting yields improvements of up to 0.65{\%} matched and 0.62{\%} mismatched accuracies for a BERT text classifier on MNLI, a practical natural language inference dataset.",
}
@misc{noriegaatala2021neural,
      title={Neural Architectures for Biological Inter-Sentence Relation Extraction},
      author={Enrique Noriega-Atala and Peter M. Lovett and Clayton T. Morrison and Mihai Surdeanu},
      year={2021},
      eprint={2112.09288},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@article{10.1162/coli_a_00463,
    author = {Tang, Zheng and Surdeanu, Mihai},
    title = "{It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers}",
    journal = {Computational Linguistics},
    volume = {49},
    number = {1},
    pages = {117-156},
    year = {2023},
    month = {03},
    abstract = "{We propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relations that explain the decisions of the relation classifier. We also convert the model outputs to rules to bring global explanations to this approach. This sequence model is trained using a hybrid strategy: supervised, when supervision from pre-existing patterns is available, and semi-supervised otherwise. In the latter situation, we treat the sequence model’s labels as latent variables, and learn the best assignment that maximizes the performance of the relation classifier. We evaluate the proposed approach on the two datasets and show that the sequence model provides labels that serve as accurate explanations for the relation classifier’s decisions, and, importantly, that the joint training generally improves the performance of the relation classifier. We also evaluate the performance of the generated rules and show that the new rules are a great add-on to the manual rules and bring the rule-based system much closer to the neural models.}",
    issn = {0891-2017},
    doi = {10.1162/coli_a_00463},
    url = {https://doi.org/10.1162/coli\_a\_00463},
    eprint = {https://direct.mit.edu/coli/article-pdf/49/1/117/2068962/coli\_a\_00463.pdf},
}
@inproceedings{bastan2022-sume,
  title={SuMe: A Dataset Towards Summarizing Biomedical Mechanisms},
  author={Bastan, Mohaddeseh and Shankar, Nishant and Surdeanu, Mihai and Balasubramanian, Niranjan},
  booktitle={Proceedings of the 2022 LREC Conference},
  year={2022},
  url={http://clulab.org/papers/SuMe_LREC2022.pdf}
}

@inproceedings{bastan2023-structural,
  title={NEUROSTRUCTURAL DECODING: Neural Text Generation with Structural Constraints},
  author={Bastan, Mohaddeseh and Surdeanu, Mihai and Balasubramanian, Niranjan},
  booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)},
  year={2023},
  url={https://aclanthology.org/2023.acl-long.528.pdf}
}

@inproceedings{rahimi2022bird,
  title={Do Transformer Networks Improve the Discovery of Rules from Text?},
  author={Rahimi, Mahdi and Surdeanu, Mihai},
  booktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
  year={2022},
  url={http://clulab.org/papers/bird.pdf},
  url_Poster={http://clulab.org/papers/can_poster.pdf}
}
@inproceedings{bridgephrases-identification2022,
  title={A STEP towards Interpretable Multi-Hop Reasoning: Bridge Phrase Identification and Query Expansion},
  author={Fan Luo and
        Mihai Surdeanu},
  booktitle = {The 13th edition of Language Resources and Evaluation Conference Processing},
  year={2022},
  abstract = {We propose an unsupervised method for the identification of bridge phrases in multi-hop question answering (QA). Our method
constructs a graph of noun phrases from the question and the available context, and applies the Steiner tree algorithm to identify
the minimal sub-graph that connects all question phrases. Nodes in the sub-graph that bridge loosely-connected or disjoint
subsets of question phrases due to low-strength semantic relations are extracted as bridge phrases. The identified bridge phrases
are then used to expand the query based on the initial question, helping in increasing the relevance of evidence that has little
lexical overlap or semantic relation with the question. Through an evaluation on HotpotQA(Yang et al., 2018), a popular dataset
for multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using
the retrieved sentences; and (c) effective and faithful explanations when answers are provided.},
  organization={European Language Resource Association (ELRA)},
  url={http://clulab.org/papers/bridgephrases.pdf}
}

@inproceedings{alexeeva-etal-2022-combining,
    title = "Combining Extraction and Generation for Constructing Belief-Consequence Causal Links",
    author = "Alexeeva, Maria  and
      Beal Cohen, Allegra A.  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the Third Workshop on Insights from Negative Results in NLP",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.insights-1.22",
    pages = "159--164",
    abstract = "In this paper, we introduce and justify a new task{---}causal link extraction based on beliefs{---}and do a qualitative analysis of the ability of a large language model{---}InstructGPT-3{---}to generate implicit consequences of beliefs. With the language model-generated consequences being promising, but not consistent, we propose directions of future work, including data collection, explicit consequence extraction using rule-based and language modeling-based approaches, and using explicitly stated consequences of beliefs to fine-tune or prompt the language model to produce outputs suitable for the task.",
}
@inproceedings{zupon2022lparsinglrec,
	title={Automatic Correction of Syntactic Dependency Annotation Differences},
	author={Zupon, Andrew and Carnie, Andrew and Hammond, Michael and Surdeanu, Mihai},
	booktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
	year={2022},
	url={http://clulab.org/papers/lrec-parsing.pdf}
}

@inproceedings{https://doi.org/10.48550/arxiv.2205.15281,
  doi = {10.48550/ARXIV.2205.15281},
  url = {https://arxiv.org/abs/2205.15281},
  author = {Noriega-Atala, Enrique and Surdeanu, Mihai and Morrison, Clayton T.},
  title = {Learning Open Domain Multi-hop Search Using Reinforcement Learning},
  booktitle = "Proceedings of the Workshop on Structured and Unstructured Knowledge Integration",
  month = jul,
  year = "2022",
  address = "Seattle, Washington",
  publisher = "Association for Computational Linguistics",
}

@inproceedings{vacareanu2022synthlrec,
        title={From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction},
        author={Vacareanu, Robert and Valenzuela-Esc\'{a}rcega, Marco A. and Barbosa, George and Sharp, Rebecca and Surdeanu, Mihai},
        booktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
        year={2022},
        url={https://arxiv.org/abs/2202.00475},
}

@Article{park2022geo,
  title     = {Answering Geosciences Research Questions at a Global Scale via a Hybrid Machine-Human Learning Approach: A Case Study of the Link between Climate and Volcanism},
  author  = {Park, Seongjin and Carrapa, Barbara and Ducea, Mihai N. and Surdeanu, Mihai and Hayes, Robert and Collins, Dan},
  journal = {GSA Today},
  url = {https://www.geosociety.org/GSA/Publications/GSA_Today/GSA/GSAToday/science/G528A/article.aspx},
  doi = {https://doi.org/10.1130/GSATG528A.1},
  year = {2022}
}

@inproceedings{bastan-etal-2022-bionli,
    title = "BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples",
    author = "Bastan, Mohaddeseh and Surdeanu, Mihai and Balasubramanian, Niranjan ",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    year = "2022",
    url = "https://paperswithcode.com/paper/bionli-generating-a-biomedical-nli-dataset",
}

@inproceedings{kwak-etal-2022-legalnli,
    title = "Validity Assessment of Legal Will Statements as Natural Language Inference",
    author = "Kwak, Alice S. and Israelsen, Jacob O. and Morrison, Clayton T. and Bambauer, Derek E. and Surdeanu, Mihai",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    year = "2022",
    url = "http://clulab.org/papers/kwak2022.pdf",
}
@inproceedings{acl2023-bootstrapping-zheng,
    title = "Bootstrapping Neural Relation and Explanation Classifiers",
    author = "Zheng Tang  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)",
    month = jul,
    year = "2023",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-short.5.pdf",
}
@inproceedings{alexeeva-etal-2020-mathalign,
    title = "{M}ath{A}lign: Linking Formula Identifiers to their Contextual Natural Language Descriptions",
    author = "Alexeeva, Maria  and
      Sharp, Rebecca  and
      Valenzuela-Esc{\'a}rcega, Marco A.  and
      Kadowaki, Jennifer  and
      Pyarelal, Adarsh  and
      Morrison, Clayton",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2020.lrec-1.269",
    pages = "2204--2212",
    abstract = "Extending machine reading approaches to extract mathematical concepts and their descriptions is useful for a variety of tasks, ranging from mathematical information retrieval to increasing accessibility of scientific documents for the visually impaired. This entails segmenting mathematical formulae into identifiers and linking them to their natural language descriptions. We propose a rule-based approach for this task, which extracts LaTeX representations of formula identifiers and links them to their in-text descriptions, given only the original PDF and the location of the formula of interest. We also present a novel evaluation dataset for this task, as well as the tool used to create it.",
    language = "English",
    ISBN = "979-10-95546-34-4",
}
@inproceedings{
    alexeeva-et-al-2023-annotating,
    title={Annotating and Training for Population Subjective Views},
    author={Alexeeva, Maria and Hyland, Caroline and Alcock, Keith and Beal Cohen,  Allegra A. and Kanyamahanga, Hubert and Anni, Isaac Kobby and Surdeanu, Mihai},
    booktitle={13th Workshop on Computational Approaches to Subjectivity, Sentiment {\&} Social Media Analysis},
    year={2023},
    url={http://clulab.org/papers/wassa2023-beliefs.pdf}
}
@Misc{alexeeva-et-al-2023-extracting-crop,
    author = {Alexeeva, Maria and Joshi, Vijaya R and Kanyamahanga, Hubert and Anni, Isaac Kobby and Alcock, Keith and Hoogenboom, Gerrit and Surdeanu, Mihai},
    title = {Extracting Crop Model Parameters from Literature Using Natural Language Processing},
    howpublished= {Presented at AI in Agriculture: Innovation and Discovery to Equitably Meet Producer Needs and Perceptions Conference, Orlando, Florida},
    url_Poster = {http://clulab.org/papers/ai-in-agro-poster.pdf},
    url_Abstract = {http://clulab.org/papers/ai-in-agriculture2023-submitted-abstract.pdf}
    year = {2023}
}
@inproceedings{song-etal-2024-metadata,
    title = "Metadata Enhancement Using Large Language Models",
    author = "Song, Hyunju  and
      Bethard, Steven  and
      Thomer, Andrea",
    editor = "Ghosal, Tirthankar  and
      Singh, Amanpreet  and
      Waard, Anita  and
      Mayr, Philipp  and
      Naik, Aakanksha  and
      Weller, Orion  and
      Lee, Yoonjoo  and
      Shen, Shannon  and
      Qin, Yanxia",
    booktitle = "Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.sdp-1.14",
    pages = "145--154",
    keywords = {workshop paper, term normalization},
}
@inproceedings{crum-bethard-2024-hinoki,
    title = "hinoki at {S}em{E}val-2024 Task 7: Numeral-Aware Headline Generation ({E}nglish)",
    author = "Crum, Hinoki  and
      Bethard, Steven",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.semeval-1.6",
    doi = "10.18653/v1/2024.semeval-1.6",
    pages = "34--39",
    keywords = {shared task paper},
}
@inproceedings{su-etal-2024-semi,
    title = "Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning",
    author = "Su, Xin  and
      Le, Tiep  and
      Bethard, Steven  and
      Howard, Phillip",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.475",
    doi = "10.18653/v1/2024.naacl-long.475",
    pages = "8597--8613",
    keywords = {question answering},
    note = {[Acceptance rate 23\%]},
}
@inproceedings{zhang-etal-2024-improving-toponym,
    title = "Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries",
    author = "Zhang, Zeyu  and
      Laparra, Egoitz  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-short.3",
    doi = "10.18653/v1/2024.naacl-short.3",
    pages = "35--44",
    keywords = {geospatial normalization, information extraction},
    note = {[Acceptance rate 23\%]},
}
@proceedings{clinicalnlp-2024-clinical,
    title = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
    editor = "Naumann, Tristan  and
      Ben Abacha, Asma  and
      Bethard, Steven  and
      Roberts, Kirk  and
      Bitterman, Danielle",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.clinicalnlp-1.0",
    keywords = "health",
}
@proceedings{findings-2024-findings-association,
    title = "Findings of the Association for Computational Linguistics: NAACL 2024",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-naacl.0",
}
@proceedings{naacl-2024-long,
    title = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.0",
}
@proceedings{naacl-2024-short,
    title = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-short.0",
}
@incollection{Bethard2024,
author="Bethard, Steven",
editor="Xu, Hua
and Demner Fushman, Dina",
title="Machine Learning and Deep Learning Algorithms",
bookTitle="Natural Language Processing in Biomedicine: A Practical Guide",
year="2024",
publisher="Springer International Publishing",
address="Cham",
pages="43--76",
isbn="978-3-031-55865-8",
doi="10.1007/978-3-031-55865-8_3",
url="https://doi.org/10.1007/978-3-031-55865-8_3",
keywords={machine learning},
}
@article{zhang_survey_2024,
	title = {A survey on geocoding: algorithms and datasets for toponym resolution},
	issn = {1574-0218},
	shorttitle = {A survey on geocoding},
	url = {https://doi.org/10.1007/s10579-024-09730-2},
	doi = {10.1007/s10579-024-09730-2},
	language = {en},
	urldate = {2024-06-12},
	journal = {Language Resources and Evaluation},
	author = {Zhang, Zeyu and Bethard, Steven},
	month = jun,
	year = {2024},
	keywords = {Geocoding, Geographical entity normalization, Toponym resolution},
}
@article{barbati-etal-2024-examining,
author = {Juliana L. Barbati and Stephen A. Rains and Kate Kenski and Yotam Shmargad and Steven Bethard and Kevin Coe},
title = {Examining the Dynamics of Uncivil Discourse Between Sub-National Political Officials and the Public on Twitter},
journal = {Mass Communication and Society},
volume = {0},
number = {0},
pages = {1-20},
month = feb,
year = {2024},
publisher = {Routledge},
url = {https://doi.org/10.1080/15205436.2024.2313095},
keywords = {social media, civility},
}
@inproceedings{su-etal-2023-fusing,
    title = "Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering",
    author = "Su, Xin  and
      Howard, Phillip  and
      Hakim, Nagib  and
      Bethard, Steven",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-emnlp.67",
    doi = "10.18653/v1/2023.findings-emnlp.67",
    pages = "948--966",
    keywords = {timelines, question answering},
}
@proceedings{clinicalnlp-2023-clinical,
    title = "Proceedings of the 5th Clinical Natural Language Processing Workshop",
    editor = "Naumann, Tristan  and
      Ben Abacha, Asma  and
      Bethard, Steven  and
      Roberts, Kirk  and
      Rumshisky, Anna",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.clinicalnlp-1.0",
    keywords = {health applications},
}
@inproceedings{gonzalez-lopez-bethard-2023-transformer,
    title = "Transformer-based cynical expression detection in a corpus of {S}panish {Y}ou{T}ube reviews",
    author = "Gonzalez-Lopez, Samuel  and
      Bethard, Steven",
    booktitle = "Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.wassa-1.18",
    pages = "194--201",
    keywords = {workshop paper, social media, sentiment},
}
@inproceedings{zhang-bethard-2023-improving,
    title = "Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution",
    author = "Zhang, Zeyu  and
      Bethard, Steven",
    booktitle = "Proceedings of the The 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.starsem-1.6",
    pages = "48--60",
    keywords = {locations, information extraction},
    note = {[Acceptance rate 47\%]},
}
@inproceedings{bozdag-etal-2023-arizonans,
    title = "Arizonans at {S}em{E}val-2023 Task 9: Multilingual Tweet Intimacy Analysis with {XLM}-{T}",
    author = "Bozdag, Nimet Beyza  and
      Bilgis, Tugay  and
      Bethard, Steven",
    booktitle = "Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.semeval-1.230",
    pages = "1656--1659",
    keywords = {shared task paper, social media},
}
@inproceedings{bilgis-etal-2023-gallagher,
    title = "Gallagher at {S}em{E}val-2023 Task 5: Tackling Clickbait with {S}eq2{S}eq Models",
    author = "Bilgis, Tugay  and
      Bozdag, Nimet Beyza  and
      Bethard, Steven",
    booktitle = "Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.semeval-1.229",
    pages = "1650--1655",
    keywords = {shared task paper, social media},
}
@inproceedings{yao-etal-2023-textual,
    title = "Textual Entailment for Temporal Dependency Graph Parsing",
    author = "Yao, Jiarui  and
      Bethard, Steven  and
      Wright-Bettner, Kristin  and
      Goldner, Eli  and
      Harris, David  and
      Savova, Guergana",
    booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.clinicalnlp-1.25",
    pages = "191--199",
    keywords = {workshop paper, timelines, information extraction, health applications},
}
@inproceedings{ozler-bethard-2023-clulab,
    title = "clulab at {MEDIQA}-Chat 2023: Summarization and classification of medical dialogues",
    author = "Ozler, Kadir Bulut  and
      Bethard, Steven",
    booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.clinicalnlp-1.19",
    pages = "144--149",
    keywords = {shared task paper, health applications},
}
@inproceedings{miller-etal-2023-end,
    title = "End-to-end clinical temporal information extraction with multi-head attention",
    author = "Miller, Timothy  and
      Bethard, Steven  and
      Dligach, Dmitriy  and
      Savova, Guergana",
    booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.bionlp-1.28",
    pages = "313--319",
    keywords = {workshop paper, timelines, information extraction, health applications},
}
@inproceedings{wang-etal-2023-two,
    title = "Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models",
    author = "Wang, Lijing  and
      Li, Yingya  and
      Miller, Timothy  and
      Bethard, Steven  and
      Savova, Guergana",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.877",
    pages = "15746--15761",
    keywords = {machine learning},
    note = {[Acceptance rate 23\%]},
}
@article{https://doi.org/10.1002/asi.24809,
author = {Laparra, Egoitz and Binford-Walsh, Alex and Emerson, Kirk and Miller, Marc L. and López-Hoffman, Laura and Currim, Faiz and Bethard, Steven},
title = {Addressing structural hurdles for metadata extraction from environmental impact statements},
journal = {Journal of the Association for Information Science and Technology},
volume = {n/a},
number = {n/a},
pages = {},
month = jun,
year = {2023},
doi = {https://doi.org/10.1002/asi.24809},
url = {https://asistdl.onlinelibrary.wiley.com/doi/abs/10.1002/asi.24809},
keywords = {environmental policy},
}
@article{doi:10.1080/27671127.2023.2195467,
author = {Stephen A. Rains and Kate Kenski and Leah Dajches and Kaylin Duncan and Kun Yan and Yejin Shin and Jules L. Barbati and Steven Bethard and Kevin Coe and Yotam Shmargad},
title = {Engagement with incivility in tweets from and directed at local elected officials},
journal = {Communication and Democracy},
volume = {57},
number = {1},
pages = {143-152},
year  = {2023},
publisher = {Routledge},
doi = {10.1080/27671127.2023.2195467},
URL = {https://doi.org/10.1080/27671127.2023.2195467},
keywords = {social media},
}
@misc{https://doi.org/10.48550/arxiv.2210.13393,
  doi = {10.48550/ARXIV.2210.13393},
  url = {https://arxiv.org/abs/2210.13393},
  author = {Bethard, Steven},
  keywords = {machine learning},
  title = {We need to talk about random seeds},
  organization = {arXiv},
  year = {2022},
  month = oct,
}
@article{10.1093/joc/jqac037,
    author = {Rains, Stephen A and Harwood, Jake and Shmargad, Yotam and Kenski, Kate and Coe, Kevin and Bethard, Steven},
    title = {Engagement with partisan Russian troll tweets during the 2016 U.S. presidential election: a social identity perspective},
    journal = {Journal of Communication},
    volume = {73},
    number = {1},
    pages = {38-48},
    year = {2022},
    month = {12},
    issn = {0021-9916},
    doi = {10.1093/joc/jqac037},
    url = {https://doi.org/10.1093/joc/jqac037},
    keywords = {social media},
}
@article{EMERSON2022106879,
title = {Toward NEPA performance: A framework for assessing EIAs},
journal = {Environmental Impact Assessment Review},
volume = {97},
pages = {106879},
year = {2022},
issn = {0195-9255},
doi = {https://doi.org/10.1016/j.eiar.2022.106879},
url = {https://www.sciencedirect.com/science/article/pii/S0195925522001457},
author = {Kirk Emerson and Elizabeth Baldwin and Tyler A. Scott and Justin R. Pidot and Aaron M. Lien and Faiz Currim and Steven Bethard and Sudha Ram and Marc L. Miller and Laura López-Hoffman},
keywords = {environmental policy},
}
@proceedings{clinicalnlp-2022-clinical,
    title = "Proceedings of the 4th Clinical Natural Language Processing Workshop",
    editor = "Naumann, Tristan  and
      Bethard, Steven  and
      Roberts, Kirk  and
      Rumshisky, Anna",
    month = jul,
    year = "2022",
    address = "Seattle, WA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.clinicalnlp-1.0",
    keywords = {health applications},
}
@inproceedings{wang-etal-2022-ensemble,
    title = "Ensemble-based Fine-Tuning Strategy for Temporal Relation Extraction from the Clinical Narrative",
    author = "Wang, Lijing  and
      Miller, Timothy  and
      Bethard, Steven  and
      Savova, Guergana",
    booktitle = "Proceedings of the 4th Clinical Natural Language Processing Workshop",
    month = jul,
    year = "2022",
    address = "Seattle, WA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.clinicalnlp-1.11",
    doi = "10.18653/v1/2022.clinicalnlp-1.11",
    pages = "103--108",
    keywords = {workshop paper, timelines, information extraction, health applications},
}
@inproceedings{dligach-etal-2022-exploring,
    title = "Exploring Text Representations for Generative Temporal Relation Extraction",
    author = "Dligach, Dmitriy  and
      Bethard, Steven  and
      Miller, Timothy  and
      Savova, Guergana",
    booktitle = "Proceedings of the 4th Clinical Natural Language Processing Workshop",
    month = jul,
    year = "2022",
    address = "Seattle, WA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.clinicalnlp-1.12",
    doi = "10.18653/v1/2022.clinicalnlp-1.12",
    pages = "109--113",
    keywords = {workshop paper, timelines, information extraction, health applications},
}
@inproceedings{culnan-etal-2022-exploring,
    title = "Exploring transformers and time lag features for predicting changes in mood over time",
    author = "Culnan, John  and
      Romero Diaz, Damian  and
      Bethard, Steven",
    booktitle = "Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology",
    month = jul,
    year = "2022",
    address = "Seattle, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.clpsych-1.21",
    doi = "10.18653/v1/2022.clpsych-1.21",
    pages = "226--231",
    keywords = {shared task paper, social media, health applications},
}
@inproceedings{tasnim-etal-2022-team,
    title = "{TEAM}-Atreides at {S}em{E}val-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in {B}angla",
    author = "Tasnim, Nazia  and
      Shihab, Md. Istiak  and
      Shahriyar Sushmit, Asif  and
      Bethard, Steven  and
      Sadeque, Farig",
    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.semeval-1.209",
    doi = "10.18653/v1/2022.semeval-1.209",
    pages = "1524--1530",
    keywords = {shared task paper, information extraction},
}
@inproceedings{song-bethard-2022-ua,
    title = "{UA}-{KO} at {S}em{E}val-2022 Task 11: Data Augmentation and Ensembles for {K}orean Named Entity Recognition",
    author = "Song, Hyunju  and
      Bethard, Steven",
    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.semeval-1.222",
    doi = "10.18653/v1/2022.semeval-1.222",
    pages = "1608--1612",
    keywords = {shared task paper, information extraction},
}
@inproceedings{surdeanu-etal-2022-taxonomy,
    title = "Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction",
    author = "Surdeanu, Mihai  and
      Hungerford, John  and
      Chan, Yee Seng  and
      MacBride, Jessica  and
      Gyori, Benjamin  and
      Zupon, Andrew  and
      Tang, Zheng  and
      Qiu, Haoling  and
      Min, Bonan  and
      Zverev, Yan  and
      Hilverman, Caitlin  and
      Thomas, Max  and
      Andrews, Walter  and
      Alcock, Keith  and
      Zhang, Zeyu  and
      Reynolds, Michael  and
      Bethard, Steven  and
      Sharp, Rebecca  and
      Laparra, Egoitz",
    booktitle = "Proceedings of the Second Workshop on Bridging Human--Computer Interaction and Natural Language Processing",
    month = jul,
    year = "2022",
    address = "Seattle, Washington",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.hcinlp-1.1",
    doi = "10.18653/v1/2022.hcinlp-1.1",
    pages = "1--10",
    keywords = {demo paper},
}
@inproceedings{su-etal-2022-comparison,
    title = "A Comparison of Strategies for Source-Free Domain Adaptation",
    author = "Su, Xin  and
      Zhao, Yiyun  and
      Bethard, Steven",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.572",
    pages = "8352--8367",
    keywords = {domain adaptation},
    note = {[Acceptance rate 21\%]},
}
@inproceedings{bertsch-bethard-2021-detection,
    title = "Detection of Puffery on the {E}nglish {W}ikipedia",
    author = "Bertsch, Amanda  and
      Bethard, Steven",
    booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
    month = nov,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.wnut-1.36",
    pages = "329--333",
    keywords = {social media, workshop paper},
}
@inproceedings{su-bethard-2021-simplifying,
    title = "Simplifying annotation of intersections in time normalization annotation: exploring syntactic and semantic validation",
    author = "Su, Peiwen  and
      Bethard, Steven",
    booktitle = "Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.law-1.11",
    pages = "106--111",
    keywords = {timelines, annotation, workshop paper},
}
@inproceedings{zhao-etal-2021-pretrained,
    title = "Do pretrained transformers infer telicity like humans?",
    author = "Zhao, Yiyun  and
      Ngui, Jian Gang  and
      Hall Hartley, Lucy  and
      Bethard, Steven",
    booktitle = "Proceedings of the 25th Conference on Computational Natural Language Learning",
    month = nov,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.conll-1.6",
    pages = "72--81",
    keywords = {timelines, machine learning},
    note = {[Acceptance rate 23\%]},
}
@article{rains-etal-2021-hcr,
    author = {Rains, Stephen A and Shmargad, Yotam and Coe, Kevin and Kenski, Kate and Bethard, Steven},
    title = {Assessing the Russian Troll Efforts to Sow Discord on Twitter during the 2016 U.S. Election},
    journal = {Human Communication Research},
    volume = {47},
    number = {4},
    pages = {477-486},
    year = {2021},
    month = {08},
    issn = {0360-3989},
    doi = {10.1093/hcr/hqab009},
    url = {https://doi.org/10.1093/hcr/hqab009},
    keywords = {social media},
}
@inproceedings{laparra-etal-2021-semeval,
    title = "{S}em{E}val-2021 Task 10: Source-Free Domain Adaptation for Semantic Processing",
    author = {Laparra, Egoitz  and
      Su, Xin  and
      Zhao, Yiyun  and
      Uzuner, {\"O}zlem  and
      Miller, Timothy  and
      Bethard, Steven},
    booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.semeval-1.42",
    doi = "10.18653/v1/2021.semeval-1.42",
    pages = "348--356",
    keywords = {domain adaptation, negation, timelines, information extraction, health applications, shared task paper},
}
@inproceedings{su-etal-2021-university,
    title = "The {U}niversity of {A}rizona at {S}em{E}val-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation",
    author = "Su, Xin  and
      Zhao, Yiyun  and
      Bethard, Steven",
    booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.semeval-1.56",
    doi = "10.18653/v1/2021.semeval-1.56",
    pages = "458--466",
    keywords = {domain adaptation, negation, timelines, information extraction, health applications, shared task paper},
}
@inproceedings{xu-bethard-2021-triplet,
    title = "Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization",
    author = "Xu, Dongfang  and
      Bethard, Steven",
    booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.bionlp-1.2",
    pages = "11--22",
    keywords = {term normalization, workshop paper},
}
@inproceedings{lin-etal-2021-entitybert,
    title = "{E}ntity{BERT}: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain",
    author = "Lin, Chen  and
      Miller, Timothy  and
      Dligach, Dmitriy  and
      Bethard, Steven  and
      Savova, Guergana",
    booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.bionlp-1.21",
    pages = "191--201",
    keywords = {timelines, information extraction, health applications, workshop paper},
}
@inproceedings{liang-etal-2021-explainable,
    title = "Explainable Multi-hop Verbal Reasoning Through Internal Monologue",
    author = "Liang, Zhengzhong  and
      Bethard, Steven  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.naacl-main.97",
    pages = "1225--1250",
    note = {[Acceptance rate 26\%]},
    keywords = {question answering},
}
@inproceedings{yadav-etal-2021-want,
    title = "If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering",
    author = "Yadav, Vikas  and
      Bethard, Steven  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.naacl-main.363",
    pages = "4571--4581",
    note = {[Acceptance rate 26\%]},
    keywords = {question answering},
}
@proceedings{naacl-2021-2021,
    title = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.naacl-main.0",
}
@inproceedings{miller-etal-2021-domain,
    title = "Domain adaptation in practice: Lessons from a real-world information extraction pipeline",
    author = "Miller, Timothy  and
      Laparra, Egoitz  and
      Bethard, Steven",
    booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
    month = apr,
    year = "2021",
    address = "Kyiv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.adaptnlp-1.11",
    pages = "105--110",
    keywords = {domain adaptation, information extraction, workshop paper},
}
@article{gonzalez-lopez-2021-PLN,
	author = {Samuel Gonz\'{a}lez-L\'{o}pez and Steven Bethard and Francisca Cecilia Encinas Orozco and Adri\i{a}n Pastor L\'{o}pez-Monroy},
	title = {Consumer Cynicism Identification for Spanish Reviews using a Spanish Transformer Model},
	journal = {Procesamiento del Lenguaje Natural},
	volume = {66},
	number = {0},
	year = {2021},
	issn = {1989-7553},
	url = {http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6327},
	pages = {111--120},
	keywords = {social media},
}
@inproceedings{kim-bethard-2020-ttui,
    title = "{TTUI} at {S}em{E}val-2020 Task 11: Propaganda Detection with Transfer Learning and Ensembles",
    author = "Kim, Moonsung  and
      Bethard, Steven",
    booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
    month = dec,
    year = "2020",
    address = "Barcelona (online)",
    publisher = "International Committee for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.semeval-1.240",
    pages = "1829--1834",
    keywords = {shared task paper, social media},
}
@inproceedings{laparra-bethard-2020-dataset,
    title = "A Dataset and Evaluation Framework for Complex Geographical Description Parsing",
    author = "Laparra, Egoitz  and
      Bethard, Steven",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.coling-main.81",
    pages = "936--948",
    keywords = {locations, information extraction},
    note = {[Acceptance rate 35\%]},
}
@proceedings{clinicalnlp-2020-clinical,
    title = "Proceedings of the 3rd Clinical Natural Language Processing Workshop",
    editor = "Rumshisky, Anna  and
      Roberts, Kirk  and
      Bethard, Steven  and
      Naumann, Tristan",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.clinicalnlp-1.0",
    keywords = {health applications},
}
@inproceedings{wright-bettner-etal-2020-defining,
    title = "Defining and Learning Refined Temporal Relations in the Clinical Narrative",
    author = "Wright-Bettner, Kristin  and
      Lin, Chen  and
      Miller, Timothy  and
      Bethard, Steven  and
      Dligach, Dmitriy  and
      Palmer, Martha  and
      Martin, James H.  and
      Savova, Guergana",
    booktitle = "Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.louhi-1.12",
    doi = "10.18653/v1/2020.louhi-1.12",
    pages = "104--114",
    keywords = {annotation, timelines, information extraction, workshop paper},
}
@inproceedings{ozler-etal-2020-fine,
    title = "Fine-tuning for multi-domain and multi-label uncivil language detection",
    author = "Ozler, Kadir Bulut  and
      Kenski, Kate  and
      Rains, Steve  and
      Shmargad, Yotam  and
      Coe, Kevin  and
      Bethard, Steven",
    booktitle = "Proceedings of the Fourth Workshop on Online Abuse and Harms",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.alw-1.4",
    doi = "10.18653/v1/2020.alw-1.4",
    pages = "28--33",
    keywords = {social media, workshop paper},
}
@inproceedings{10.1145/3397271.3401311,
author = {Yadav, Vikas and Bethard, Steven and Surdeanu, Mihai},
title = {Having Your Cake and Eating It Too: Training Neural Retrieval for Language Inference without Losing Lexical Match},
year = {2020},
month = {7},
isbn = {9781450380164},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3397271.3401311},
doi = {10.1145/3397271.3401311},
booktitle = {Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
pages = {1625--1628},
numpages = {4},
location = {Virtual Event, China},
series = {SIGIR '20},
keywords = {question answering},
note = {[Acceptance rate 26\%]},
}
@article{xu-etal-2020-unified,
    author = {Xu, Dongfang and Gopale, Manoj and Zhang, Jiacheng and Brown, Kris and Begoli, Edmon and Bethard, Steven},
    title = {Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)-based ranking for concept normalization},
    journal = {Journal of the American Medical Informatics Association},
    year = {2020},
    month = {07},
    issn = {1527-974X},
    doi = {10.1093/jamia/ocaa080},
    url = {https://doi.org/10.1093/jamia/ocaa080},
    keywords = {health applications, term normalization},
}
@inproceedings{lin-etal-2020-bert,
    title = "A {BERT}-based One-Pass Multi-Task Model for Clinical Temporal Relation Extraction",
    author = "Lin, Chen  and
      Miller, Timothy  and
      Dligach, Dmitriy  and
      Sadeque, Farig  and
      Bethard, Steven  and
      Savova, Guergana",
    booktitle = "Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.bionlp-1.7",
    pages = "70--75",
    keywords = {workshop paper, health applications, timelines, information extraction},
}
@inproceedings{gonzalez-lopez-etal-2020-assisting,
    title = "Assisting Undergraduate Students in Writing {S}panish Methodology Sections",
    author = "Gonz{\'a}lez-L{\'o}pez, Samuel  and
      Bethard, Steven  and
      Lopez-Lopez, Aurelio",
    booktitle = "Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications",
    month = jul,
    year = "2020",
    address = "Seattle, WA, USA - Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.bea-1.11",
    pages = "115--123",
    keywords = {educational applications, workshop paper},
}
@inproceedings{xu-etal-2020-generate,
    title = "A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization",
    author = "Xu, Dongfang  and
      Zhang, Zeyu  and
      Bethard, Steven",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.748",
    pages = "8452--8464",
    note = {[Acceptance rate 23\%]},
    keywords = {health applications, term normalization},
}
@inproceedings{zhao-bethard-2020-berts,
    title = "How does {BERT}{'}s attention change when you fine-tune? An analysis methodology and a case study in negation scope",
    author = "Zhao, Yiyun  and
      Bethard, Steven",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.429",
    pages = "4729--4747",
    note = {[Acceptance rate 23\%]},
    keywords = {negation, machine learning},
}
@inproceedings{yadav-etal-2020-unsupervised,
    title = "Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering",
    author = "Yadav, Vikas  and
      Bethard, Steven  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.414",
    pages = "4514--4525",
    note = {[Acceptance rate 23\%]},
    keywords = {question answering},
}
@article{laparra-bethard-miller:2020:JAMIAOpen,
    author = {Laparra, Egoitz and Bethard, Steven and Miller, Timothy A},
    title = "{Rethinking domain adaptation for machine learning over clinical language}",
    journal = {JAMIA Open},
    year = {2020},
    month = {04},
    issn = {2574-2531},
    doi = {10.1093/jamiaopen/ooaa010},
    url = {https://doi.org/10.1093/jamiaopen/ooaa010},
    keywords = {domain adaptation, health applications},
}
@article{chen-etal:2020:JAMIA,
    author = {Lin, Chen and Bethard, Steven and Dligach, Dmitriy and Sadeque, Farig and Savova, Guergana and Miller, Timothy A},
    title = "{Does BERT need domain adaptation for clinical negation detection?}",
    journal = {Journal of the American Medical Informatics Association},
    volume = {27},
    number = {4},
    pages = {584-591},
    year = {2020},
    month = {02},
    issn = {1527-974X},
    doi = {10.1093/jamia/ocaa001},
    url = {https://doi.org/10.1093/jamia/ocaa001},
    keywords = {negation, health applications},
}
@inproceedings{yadav-etal-2019-quick,
    title = "Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering",
    author = "Yadav, Vikas  and
      Bethard, Steven  and
      Surdeanu, Mihai",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D19-1260",
    doi = "10.18653/v1/D19-1260",
    pages = "2578--2589",
    note = {[Acceptance rate 23\%]},
    keywords = {question answering},
}
@proceedings{W19-19:2019,
  editor    = {Anna Rumshisky  and  Kirk Roberts  and  Steven Bethard  and  Tristan Naumann},
  title     = {Proceedings of the 2nd Clinical Natural Language Processing Workshop},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, Minnesota, USA},
  publisher = {Association for Computational Linguistics},
  url       = {http://www.aclweb.org/anthology/W19-19},
  keywords = {health applications},
}
@InProceedings{bethard-EtAl:2019:W19-25,
  author    = {Bethard, Steven  and  Laparra, Egoitz  and  Wang, Sophia  and  Zhao, Yiyun  and  Al-Ghezi, Ragheb  and  Lien, Aaron  and  L\'{o}pez-Hoffman, Laura},
  title     = {Inferring missing metadata from environmental policy texts},
  booktitle = {Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {46--51},
  url       = {http://www.aclweb.org/anthology/W19-2506},
  keywords = {workshop paper, environmental policy},
}
@InProceedings{lin-EtAl:2019:W19-19,
  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Bethard, Steven  and  Savova, Guergana},
  title     = {A BERT-based Universal Model for Both Within- and Cross-sentence Clinical Temporal Relation Extraction},
  booktitle = {Proceedings of the 2nd Clinical Natural Language Processing Workshop},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, Minnesota, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {65--71},
  url       = {http://www.aclweb.org/anthology/W19-1908},
  keywords = {workshop paper, health applications, timelines, information extraction},
}
@InProceedings{yadav-EtAl:2019:S19-2,
  author    = {Yadav, Vikas  and  Laparra, Egoitz  and  Wang, Ti-Tai  and  Surdeanu, Mihai  and  Bethard, Steven},
  title     = {University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities},
  booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, Minnesota, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {1319--1323},
  url       = {http://www.aclweb.org/anthology/S19-2232},
  keywords = {shared task paper, locations, information extraction},
}
@InProceedings{sadeque-EtAl:2019:S19-1,
  author    = {Sadeque, Farig  and  Rains, Stephen  and  Shmargad, Yotam  and  Kenski, Kate  and  Coe, Kevin  and  Bethard, Steven},
  title     = {Incivility Detection in Online Comments},
  booktitle = {Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, Minnesota},
  publisher = {Association for Computational Linguistics},
  pages     = {283--291},
  url       = {http://www.aclweb.org/anthology/S19-1031},
  note = {[Acceptance rate 33\%]},
  keywords = {social media},
}
@InProceedings{xu-laparra-bethard:2019:S19-1,
  author    = {Xu, Dongfang  and  Laparra, Egoitz  and  Bethard, Steven},
  title     = {Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis},
  booktitle = {Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, Minnesota},
  publisher = {Association for Computational Linguistics},
  pages     = {68--74},
  url       = {http://www.aclweb.org/anthology/S19-1008},
  note = {[Acceptance rate 33\%]},
  keywords = {timelines, information extraction},
}
@InProceedings{sharp-EtAl:2019:N19-4,
  author    = {Sharp, Rebecca  and  Pyarelal, Adarsh  and  Gyori, Benjamin  and  Alcock, Keith  and  Laparra, Egoitz  and  Valenzuela-Esc\'{a}rcega, Marco A.  and  Nagesh, Ajay  and  Yadav, Vikas  and  Bachman, John  and  Tang, Zheng  and  Lent, Heather  and  Luo, Fan  and  Paul, Mithun  and  Bethard, Steven  and  Barnard, Kobus  and  Morrison, Clayton  and  Surdeanu, Mihai},
  title     = {Eidos, INDRA, \& Delphi: From Free Text to Executable Causal Models},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, Minnesota},
  publisher = {Association for Computational Linguistics},
  pages     = {42--47},
  url       = {http://www.aclweb.org/anthology/N19-4008},
  keywords = {demo paper, causal relations, timelines, locations, information extraction},
}
@InProceedings{yadav-bethard-surdeanu:2019:N19-1,
  author    = {Yadav, Vikas  and  Bethard, Steven  and  Surdeanu, Mihai},
  title     = {Alignment over Heterogeneous Embeddings for Question Answering},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)},
  month     = {6},
  year      = {2019},
  address   = {Minneapolis, Minnesota},
  publisher = {Association for Computational Linguistics},
  pages     = {2681--2691},
  url       = {http://www.aclweb.org/anthology/N19-1274},
  note = {[Acceptance rate 26\%]},
  keywords = {question answering},
}
@article{gonzalez-lopez-EtAl:2019:RCS,
  author    = {Samuel Gonz{\'{a}}lez L{\'{o}}pez and
               Aurelio L{\'{o}}pez{-}L{\'{o}}pez and
               Steven Bethard and
               Jes{\'{u}}s Miguel Garc{\'{i}}a Gorrostieta},
  title     = {A Model for Identifying Steps in Undergraduate Thesis Methodology},
  journal   = {Res. Comput. Sci.},
  volume    = {148},
  number    = {5},
  pages     = {17--24},
  year      = {2019},
  url       = {http://rcs.cic.ipn.mx/2019\_148\_5/A\%20Model\%20for\%20Identifying\%20Steps\%20in\%20Undergraduate\%20Thesis\%20Methodology.pdf},
  keywords = {educational applications},
}
@InProceedings{lin-EtAl:2018:LOUHI,
  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Amiri, Hadi  and  Bethard, Steven  and  Savova, Guergana},
  title     = {Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction},
  booktitle = {Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis},
  month     = {10},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  pages     = {165--176},
  url       = {http://www.aclweb.org/anthology/W18-5619},
  keywords = {timelines, information extraction, health applications, workshop paper},
}
@InProceedings{yadav-bethard:2018:C18-1,
  author    = {Yadav, Vikas  and  Bethard, Steven},
  title     = {A Survey on Recent Advances in Named Entity Recognition from Deep Learning models},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  month     = {8},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {2145--2158},
  url       = {http://www.aclweb.org/anthology/C18-1182},
  note = {[Acceptance rate 37\%]},
  keywords = {information extraction},
}
@proceedings{apidianaki-etal:2018:SemEval,
  editor    = {Marianna Apidianaki  and  Saif M. Mohammad  and  Jonathan May  and  Ekaterina Shutova  and  Steven Bethard  and  Marine Carpuat},
  title     = {Proceedings of The 12th International Workshop on Semantic Evaluation (SemEval-2018)},
  month     = {6},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  url       = {http://www.aclweb.org/anthology/S18-1},
}
@InProceedings{laparra-etal:2018:SemEval,
  author    = {Laparra, Egoitz  and  Xu, Dongfang  and  Elsayed, Ahmed  and  Bethard, Steven  and  Palmer, Martha},
  title     = {SemEval 2018 Task 6: Parsing Time Normalizations},
  booktitle = {Proceedings of The 12th International Workshop on Semantic Evaluation},
  month     = {6},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {88--96},
  url       = {http://www.aclweb.org/anthology/S18-1011},
  keywords  = {timelines, information extraction, shared task paper},
}
@InProceedings{yadav-sharp-bethard:2018:SEM,
  author    = {Yadav, Vikas  and  Sharp, Rebecca  and  Bethard, Steven},
  title     = {Deep Affix Features Improve Neural Named Entity Recognizers},
  booktitle = {Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics},
  month     = {6},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {167--172},
  url       = {http://www.aclweb.org/anthology/S18-2021},
  note = {[Acceptance rate 29\%]},
  keywords  = {information extraction},
}
@article{laparra-xu-bethard:2018:TACL,
        author = {Laparra, Egoitz  and Xu, Dongfang  and Bethard, Steven },
        title = {From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations},
        journal = {Transactions of the Association for Computational Linguistics},
        volume = {6},
        year = {2018},
        month = {5},
        day = {31},
        keywords = {timelines, information extraction},
        issn = {2307-387X},
        url = {https://transacl.org/ojs/index.php/tacl/article/view/1318},
        pages = {343--356}
}
@InProceedings{xu-yadav-bethard:2018:MADE,
  title = 	 {UArizona at the MADE1.0 NLP Challenge},
  author = 	 {Dongfang Xu and Vikas Yadav and Steven Bethard},
  booktitle = 	 {Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection},
  pages = 	 {57--65},
  year = 	 {2018},
  editor = 	 {Feifan Liu and Abhyuday Jagannatha and Hong Yu},
  volume = 	 {90},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {},
  month = 	 {5},
  url = 	 {http://proceedings.mlr.press/v90/xu18a.html},
  keywords = {semantic relations, information extraction, health applications, shared task paper},
}
@INPROCEEDINGS{8397017,
author={Ligaj Pradhan and Chengcui Zhang and Steven Bethard and Xin Chen},
booktitle={2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)},
title={Embedding User Behavioral Aspect in TF-IDF Like Representation},
year={2018},
volume={},
number={},
pages={262-267},
keywords={information retrieval, recommender systems},
url={http://doi.org/10.1109/MIPR.2018.00061},
ISSN={},
month={4},
note = {[Acceptance rate 20\%]},
}
@inproceedings{sadeque-xu-bethard:2018:WSDM,
 author = {Sadeque, Farig and Xu, Dongfang and Bethard, Steven},
 title = {Measuring the Latency of Depression Detection in Social Media},
 booktitle = {Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining},
 series = {WSDM '18},
 year = {2018},
 month = {2},
 isbn = {978-1-4503-5581-0},
 location = {Marina Del Rey, CA, USA},
 pages = {495--503},
 numpages = {9},
 url = {http://doi.acm.org/10.1145/3159652.3159725},
 doi = {10.1145/3159652.3159725},
 acmid = {3159725},
 publisher = {ACM},
 address = {New York, NY, USA},
  note = {[Acceptance rate 16\%]},
 keywords = {health applications, social media},
}
@Article{osborne-etal:2018:JBS,
author="Osborne, John D.
and Neu, Matthew B.
and Danila, Maria I.
and Solorio, Thamar
and Bethard, Steven J.",
title="CUILESS2016: a clinical corpus applying compositional normalization of text mentions",
journal="Journal of Biomedical Semantics",
year="2018",
month="1",
day="10",
volume="9",
number="1",
pages="2",
issn="2041-1480",
doi="10.1186/s13326-017-0173-6",
url="https://doi.org/10.1186/s13326-017-0173-6",
keywords = {annotation, term normalization, health applications},
}
@InProceedings{do-bethard-moens:2017:I17-1,
  author    = {Do, Quynh Ngoc Thi  and  Bethard, Steven  and  Moens, Marie-Francine},
  title     = {Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {11},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {90--99},
  url       = {http://www.aclweb.org/anthology/I17-1010},
  note = {[Acceptance rate 31\%]},
  keywords = {semantic relations},
}
@InProceedings{sadeque-xu-bethard:2017:CLEF,
  author = {Farig Sadeque and Dongfang Xu and Steven Bethard},
  title = {{UArizona} at the {CLEF eRisk} 2017 Pilot Task: Linear and Recurrent Models for Early Depression Detection},
  booktitle = {CEUR workshop proceedings: Working Notes of CLEF 2017 - Conference and Labs of the Evaluation Forum},
  address = {Dublin, Ireland},
  month = {9},
  year = {2017},
  url = {http://ceur-ws.org/Vol-1866/paper_58.pdf},
  keywords = {health applications, social media, shared task paper},
}
@INPROCEEDINGS{pradhan-zhang-bethard:2017:IRI,
author = {Ligaj Pradhan and Chengcui Zhang and Steven Bethard},
booktitle = {2017 IEEE International Conference on Information Reuse and Integration (IRI)},
title = {Infusing Latent User-Concerns from User Reviews into Collaborative Filtering},
year = {2017},
volume = {},
number = {},
pages = {471-477},
doi = {10.1109/IRI.2017.24},
url = {http://doi.ieeecomputersociety.org/10.1109/IRI.2017.24},
month={8},
note = {[Acceptance rate 29\%]},
keywords = {information retrieval, recommender systems},
}
@InProceedings{lin-EtAl:2017:BioNLP17,
  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Bethard, Steven  and  Savova, Guergana},
  title     = {Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks},
  booktitle = {BioNLP 2017},
  month     = {8},
  year      = {2017},
  address   = {Vancouver, Canada,},
  publisher = {Association for Computational Linguistics},
  pages     = {322--327},
  url       = {http://www.aclweb.org/anthology/W17-2341},
  keywords = {timelines, information extraction, health applications, workshop paper},
}
@InProceedings{miller-EtAl:2017:BioNLP17,
  author    = {Miller, Timothy  and  Bethard, Steven  and  Amiri, Hadi  and  Savova, Guergana},
  title     = {Unsupervised Domain Adaptation for Clinical Negation Detection},
  booktitle = {BioNLP 2017},
  month     = {8},
  year      = {2017},
  address   = {Vancouver, Canada,},
  publisher = {Association for Computational Linguistics},
  pages     = {165--170},
  url       = {http://www.aclweb.org/anthology/W17-2320},
  keywords = {negation, domain adaptation, health applications, workshop paper},
}
@InProceedings{bethard-EtAl:2017:SemEval,
  author    = {Bethard, Steven  and  Savova, Guergana  and  Palmer, Martha  and  Pustejovsky, James},
  title     = {SemEval-2017 Task 12: Clinical TempEval},
  booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},
  month     = {8},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {565--572},
  url       = {http://www.aclweb.org/anthology/S17-2093},
  keywords = {timelines, information extraction, health applications, domain adaptation, shared task paper},
}
@proceedings{SemEval:2017,
  editor    = {Steven Bethard  and  Marine Carpuat  and  Marianna Apidianaki  and  Saif M. Mohammad  and  Daniel Cer  and  David Jurgens},
  title     = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},
  month     = {8},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  url       = {http://www.aclweb.org/anthology/S17-2},
}
@InProceedings{viani-EtAl:2017:AIME,
author="Viani, Natalia
and Miller, Timothy A.
and Dligach, Dmitriy
and Bethard, Steven
and Napolitano, Carlo
and Priori, Silvia G.
and Bellazzi, Riccardo
and Sacchi, Lucia
and Savova, Guergana K.",
editor="ten Teije, Annette
and Popow, Christian
and Holmes, John H.
and Sacchi, Lucia",
title="Recurrent Neural Network Architectures for Event Extraction from Italian Medical Reports",
bookTitle="Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings",
year="2017",
publisher="Springer International Publishing",
address="Cham",
pages="198--202",
isbn="978-3-319-59758-4",
doi="10.1007/978-3-319-59758-4_21",
url="https://doi.org/10.1007/978-3-319-59758-4_21",
note = {[Acceptance rate 39\%]},
keywords = {timelines, information extraction, health applications},
}
@article{miller-EtAl:2017:JBI,
title = "Towards generalizable entity-centric clinical coreference resolution ",
journal = "Journal of Biomedical Informatics ",
volume = "69",
number = "",
pages = "251 - 258",
year = "2017",
note = "",
issn = "1532-0464",
doi = "https://doi.org/10.1016/j.jbi.2017.04.015",
url = "http://www.sciencedirect.com/science/article/pii/S1532046417300850",
author = "Timothy Miller and Dmitriy Dligach and Steven Bethard and Chen Lin and Guergana Savova",
keywords = {coreference, health applications},
}
@InProceedings{dligach-EtAl:2017:EACLshort,
  author    = {Dligach, Dmitriy  and  Miller, Timothy  and  Lin, Chen  and  Bethard, Steven  and  Savova, Guergana},
  title     = {Neural Temporal Relation Extraction},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {4},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {746--751},
  url       = {http://www.aclweb.org/anthology/E17-2118},
  note = {[Acceptance rate 24\%]},
  keywords = {timelines, information extraction, health applications},
}
@article{pradhan2016extracting,
  title={Extracting Hierarchy of Coherent User-Concerns to Discover Intricate User Behavior from User Reviews},
  author={Pradhan, Ligaj and Zhang, Chengcui and Bethard, Steven},
  journal={International Journal of Multimedia Data Engineering and Management (IJMDEM)},
  volume={7},
  number={4},
  pages={63--80},
  year={2016},
  publisher={IGI Global},
  url={https://dx.doi.org/10.4018/IJMDEM.2016100104},
  keywords={information retrieval, recommender systems},
}
@proceedings{ClinicalNLP:2016,
  editor    = {Anna Rumshisky  and  Kirk Roberts  and  Steven Bethard  and  Tristan Naumann},
  title     = {Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP)},
  month     = {12},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  url       = {http://aclweb.org/anthology/W16-42},
  keywords = {health applications},
}
@InProceedings{do-bethard-moens:2016:COLING,
  author    = {Do, Quynh Ngoc Thi  and  Bethard, Steven  and  Moens, Marie-Francine},
  title     = {Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {12},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {1275--1284},
  url       = {http://aclweb.org/anthology/C16-1121},
  note = {[Acceptance rate 32\%]},
  keywords = {semantic relations, domain adaptation},
}
@InProceedings{sadeque-EtAl:2016:SocialNLP,
  author    = {Sadeque, Farig  and  Pedersen, Ted  and  Solorio, Thamar  and  Shrestha, Prasha  and  Rey-Villamizar, Nicolas  and  Bethard, Steven},
  title     = {Why Do They Leave: Modeling Participation in Online Depression Forums},
  booktitle = {Proceedings of The Fourth International Workshop on Natural Language Processing for Social Media},
  month     = {11},
  year      = {2016},
  address   = {Austin, TX, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {14--19},
  url       = {http://aclweb.org/anthology/W16-6203},
  keywords = {health applications, social media, workshop paper},
}
@InProceedings{reyvillamizar-EtAl:2016:LOUHI,
  author    = {Rey-Villamizar, Nicolas  and  Shrestha, Prasha  and  Sadeque, Farig  and  Bethard, Steven  and  Pedersen, Ted  and  Mukherjee, Arjun  and  Solorio, Thamar},
  title     = {Analysis of Anxious Word Usage on Online Health Forums},
  booktitle = {Proceedings of the Seventh International Workshop on Health Text Mining and Information Analysis},
  month     = {11},
  year      = {2016},
  address   = {Auxtin, TX},
  publisher = {Association for Computational Linguistics},
  pages     = {37--42},
  url       = {http://aclweb.org/anthology/W16-6105},
  keywords = {health applications, social media, workshop paper},
}
@InProceedings{do-bethard-moens:2016:UBLP,
  author    = {Do, Quynh Ngoc Thi  and  Bethard, Steven  and  Moens, Marie-Francine},
  title     = {Visualizing the Content of a Children's Story in a Virtual World: Lessons Learned},
  booktitle = {Proceedings of the Workshop on Uphill Battles in Language Processing: Scaling Early Achievements to Robust Methods},
  month     = {11},
  year      = {2016},
  address   = {Austin, TX},
  publisher = {Association for Computational Linguistics},
  pages     = {39--42},
  url       = {http://aclweb.org/anthology/W16-6009},
  keywords = {coreference, semantic relations, educational applications, workshop paper},
}
@InProceedings{lin-EtAl:2016:BioNLP16,
  author    = {Lin, Chen  and  Miller, Timothy  and  Dligach, Dmitriy  and  Bethard, Steven  and  Savova, Guergana},
  title     = {Improving Temporal Relation Extraction with Training Instance Augmentation},
  booktitle = {Proceedings of the 15th Workshop on Biomedical Natural Language Processing},
  month     = {8},
  year      = {2016},
  address   = {Berlin, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {108--113},
  url       = {http://anthology.aclweb.org/W16-2914},
  keywords = {timelines, information extraction, health applications, workshop paper},
}
@InProceedings{sapkota-EtAl:2016:P16-1,
  author    = {Sapkota, Upendra  and  Solorio, Thamar  and  Montes, Manuel  and  Bethard, Steven},
  title     = {Domain Adaptation for Authorship Attribution: Improved Structural Correspondence Learning},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {8},
  year      = {2016},
  address   = {Berlin, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {2226--2235},
  url       = {http://www.aclweb.org/anthology/P16-1210},
  note = {[Acceptance rate 28\%]},
  keywords = {authorship analysis, domain adaptation},
}