Skip to content

LapDevelopment_Tree

StephanOepen edited this page Jul 24, 2014 · 19 revisions

Background

Segmentation (Including Tokenization)

  • NLTK Punkt: validated (twice)
  • NLTK Tokenizer: wrapped (not validated)
  • tokenizer Segmenter:
  • REPP Tokenizer: validated

Tagging

  • NLTK Tagger: wrapped (not validated)

  • HunPos: wrapped (not validated)

Parsing

  • Malt: wrapped (not validated)

Interfacing

  • Corpus Import: to be revisited
  • CoNLL Export: wrapped (not validated)
Clone this wiki locally