NEW!!! (03.04.14): WSD by maximizing sense similarity with various similarity measures.

Python Implementations of Word Sense Disambiguation (WSD) technologies:

• Lesk algorithms
  • Original Lesk (Lesk, 1986)
  • Adapted/Extended Lesk (Banerjee and Pederson, 2002/2003)
  • Simple Lesk (with definition, example(s) and hyper+hyponyms)
  • Cosine Lesk (use cosines to calculate overlaps instead of using raw counts)
• Maximizing Similarity (see also, http://goo.gl/MG8ZpE)
  • Path similarity (Wu-Palmer, 1994; Leacock and Chodorow, 1998)
  • Information Content (Resnik, 1995; Jiang and Corath, 1997; Lin, 1998)
• Supervised WSD (in progress)
  • Support Vector Machine (Lee, Ng and Chia 2004)
• Vector Space Models (in progress)
  • LSI/LSA
  • Topic Models, LDA (Li et al. 2012)
  • NMF
• Graph based Models (in wishlist)
  • Babelfly (Moro et al. 2014)
• Baselines
  • Random sense
  • First NLTK sense
  • Highest lemma counts

(NOTE: requires NLTK, goto http://nltk.org/install.html. Also, note that as of 30.10.13, NLTK has changed Synset object properties to methods, see http://goo.gl/hO79KO)

$ cd pywsd/
$ ls
baseline.py   cosine.py   lesk.py   README.md   test_wsd.py
$ python
>>> from lesk import simple_lesk
>>> sent = 'I went to the bank to deposit my money'
>>> ambiguous = 'bank'
>>> answer = simple_lesk(sent, ambiguous)
>>> print answer
Synset('depository_financial_institution.n.01')
>>> print answer.definition()
a financial institution that accepts deposits and channels the money into lending activities

29.05.14 (user request):

• Automatically lemmatize ambiguous_word parameter because without it being a lemma, wn.synsets(ambiguous_word) breaks the system.

15.05.14 (bugfix):

• Added try-excepts to allow old NLTK Synset properties.

15.04.14:

• Changed Synset properties to methods adhering to new NLTK version (see see http://goo.gl/hO79KO)
• Added N-best results, pywsd now outputs ranked list of synsets (possible with normalized scores too), see test_wsd.py

03.04.14:

• Added similarity based WSD methods.

To cite pywsd:

Liling Tan. 2014. Pywsd: Python Implementations of Word Sense Disambiguation (WSD) Technologies [software]. Retrieved from https://github.com/alvations/pywsd

In bibtex:

@misc{pywsd14,
author =   {Liling Tan},
title =    {Pywsd: Python Implementations of Word Sense Disambiguation (WSD) Technologies [software]},
howpublished = {https://github.com/alvations/pywsd}},
year = {2014}
}

• Michael Lesk. 1986. Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone. In Proceedings of the 5th annual international conference on Systems documentation (SIGDOC '86), Virginia DeBuys (Ed.). ACM, New York, NY, USA, 24-26. DOI=10.1145/318723.318728 http://doi.acm.org/10.1145/318723.318728

• Satanjeev Banerjee and Ted Pedersen. 2002. An Adapted Lesk Algorithm for Word Sense Disambiguation Using WordNet. In Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing (CICLing '02), Alexander F. Gelbukh (Ed.). Springer-Verlag, London, UK, UK, 136-145.

• Satanjeev Banerjee and Ted Pedersen. 2003. Extended gloss overlaps as a measure of semantic relatedness. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, pages 805–810, Acapulco.

• Jay J. Jiang and David W. Conrath. 1997. Semantic similarity based on corpus statistics and lexical taxonomy. In Proceedings of International Conference on Research in Computational Linguistics, Taiwan.

• Claudia Leacock and Martin Chodorow. 1998. Combining local context and WordNet similarity for word sense identification. In Fellbaum 1998, pp. 265–283.

• Lee, Yoong Keok, Hwee Tou Ng, and Tee Kiah Chia. "Supervised word sense disambiguation with support vector machines and multiple knowledge sources." Senseval-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text. 2004.

• Dekang Lin. 1998. An information-theoretic definition of similarity. In Proceedings of the 15th International Conference on Machine Learning, Madison, WI.

• Linlin Li, Benjamin Roth and Caroline Sporleder. 2010. Topic Models for Word Sense Disambiguation and Token-based Idiom Detection. The 48th Annual Meeting of the Association for Computational Linguistics (ACL). Uppsala, Sweden.

• Andrea Moro, Roberto Navigli, Francesco Maria Tucci and Rebecca J. Passonneau. 2014. Annotating the MASC Corpus with BabelNet. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14). Reykjavik, Iceland.

• Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python (1st ed.). O'Reilly Media, Inc..