How to Download and Run this model locally: README



Reference Papers:

Andrea Gesmundo, Tanja Samardzic. 2012. Lemmatisation as a Tagging Task. ACL 2012.
pdf   bibtex

Andrea Gesmundo. 2011. Bidirectional Sequence Classification for Tagging Tasks with Guided Learning. Proceedings of TALN 2011.
pdf   bibtex

Andrea Gesmundo. 2009. Bidirectional Sequence Classification for Part of Speech Tagging. Evalita 2009: Evaluation of NLP and Speech Tools for Italian.
pdf   bibtex



Part of Speech Tagger:

Accuracy Trained on Corpus
Croatian 93.68% MULTEXT-East v4
Czech 96.87% MULTEXT-East v4
English 97.01% MULTEXT-East v4
Estonian 96.32% MULTEXT-East v4
French 97.89% French Treebank
Hungarian 97.13% MULTEXT-East v4
Italian 95.85% Evalita 2009 POS corpus
Polish 97.61% MULTEXT-East v4
Romanian 97.29% MULTEXT-East v4
Serbian 93.68% MULTEXT-East v4
Slovene 96.80% MULTEXT-East v4


Lemmatizer:

Accuracy Trained on Corpus
Croatian 97.18% MULTEXT-East v4
Czech 97.68% MULTEXT-East v4
English 99.59% MULTEXT-East v4
Estonian 97.36% MULTEXT-East v4
Hungarian 97.47% MULTEXT-East v4
Polish 96.82% MULTEXT-East v4
Romanian 98.28% MULTEXT-East v4
Serbian 97.18% MULTEXT-East v4
Slovene 98.13% MULTEXT-East v4