English

Lexica

All lexica can be found here:

• en-ambiguity-classes-simplified.xz
  : ambiguity classes for part-of-speech tagging with simplified word forms.
• en-ambiguity-classes-simplified-lowercase.xz
  : ambiguity classes for part-of-speech tagging with simplified lowercase word forms.
• en-brown-clusters-simplified-lowercase.xz
  : brown clusters with simplified lowercase word forms.
• en-named-entity-gazetteers-simplified.xz
  : gazetteers for named entity recognition with simplified word forms.
• en-named-entity-gazetteers-simplified-lowercase.xz
  : gazetteers for named entity recognition with simplified lowercase word forms.
• en-stop-words-simplified-lowercase.xz
  : stop words with simplified lowercase word forms.
• en-word-embeddings-undigitalized.xz
  : word embeddings with undigitalized word forms.

Models

All models can be found here:

• en-pos.xz: part-of-speech tagging.
• en-ner.xz: named entity recognition.
• en-dep.xz: dependency parsing.

Models are trained on the following corpora.