Automatic Identification of Infrequent Word Senses

What it is about

The paper ranks the senses of a word without any sense-tagged data, using a thesaurus built from raw text (a BNC thesaurus of distributional neighbours) and WordNet similarity. The ranking is then used to remove senses that are probably absent from a text. The authors test the removal on SemCor and on the SENSEVAL-2 English all-words sample. Random filtering of polysemous nouns in SemCor would be right 38% of the time, and the method does better at every setting, with most of the removed senses rarely used. On SemCor nouns, 77% of sense types do not occur, and the method still beats that baseline at each level, though with fewer types removed. The main aim is domain text: with two domain corpora, the removed senses were mostly senses from outside the domain.

Ideas

• I1. onto/src/wsd.rs: add a domain-aware filter that removes WordNet senses with a lexfile or domain label that never occurs in the target genre. Measure the WSD accuracy on the EWT test set (which mixes genres) and on a single-genre subset, with the filter on and off, and run twice to confirm.
• I2. Ranking check: compare the current predominant-sense ranking in onto with a ranking by the Lesk gloss overlap the paper favours for nouns, verbs, adjectives and adverbs. Report the agreement and the accuracy on EWT with each ranking.
• I3. Thesaurus from open text: build neighbours for nouns from en parses of an open corpus (not the BNC), and measure how often the removed sense is one that the test corpus never uses; the SemCor figure (38% random) is the baseline. Use SemCor only as a test set.

For Mova

The touch points are onto/src/wsd.rs (the predominant sense and extended Lesk already there), onto lexfile and domain data, and en parses for the neighbour thesaurus. The chapter is 37. Register and variation for genre effects, with 10. Word classes for part-of-speech. The BNC thesaurus and SemCor are NC; they are used for tests and measurements only. Measure first the genre filter on EWT with two identical runs.

Topics: Word sense disambiguation

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.3115/1220355.1220532

@inproceedings{mccarthy2004automatic,
  title = {{Automatic Identification of Infrequent Word Senses}},
  author = {McCarthy, Diana and Koeling, Rob and Weeds, Julie and Carroll, John},
  booktitle = {COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics},
  year = {2004},
  doi = {10.3115/1220355.1220532},
  url = {https://doi.org/10.3115/1220355.1220532}
}

References

17 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eneko Agirre and Oier Lopez de Lacalle. 2003. Clustering wordnet word senses. In Recent Advances in Natural Language Processing, Borovets, Bulgaria. find
2. Edward Briscoe and John Carroll. 2002. Robust accurate statistical annotation of general text. In Proceedings of the Third International Conference on Language Resources and Evaluation (LREC), pages 1499–1504, Las Palmas, Canary Islands, Spain. find
3. Paul Buitelaar and Bogdan Sacaleanu. 2001. Ranking and selecting synsets by domain relevance. In Proceedings of WordNet and Other Lexical Resources: Applications, Extensions and Customizations, NAACL 2001 Workshop, Pittsburgh, PA. find
4. Véronique Hoste, Anne Kool, and Walter Daelemans. 2001. Classifier optimization and combination in the English all words task. In Proceedings of the SENSEVAL -2 workshop, pages 84–86. find
5. Jay Jiang and David Conrath. 1997. Semantic similarity based on corpus statistics and lexical taxonomy. In International Conference on Research in Computational Linguistics, Taiwan. find
6. Adam Kilgarriff and Joseph Rosenzweig. 2000. English SENSEVAL: Report and results. In Proceedings of LREC-2000, Athens, Greece. find
7. Mirella Lapata and Chris Brew. 2004. Verb class disambiguation using informative priors. Computational Linguistics, 30(1):45–75. find
8. Dekang Lin. 1998. Automatic retrieval and clustering of similar words. In Proceedings of COLING-ACL 98, Montreal, Canada. find
9. Bernardo Magnini and Gabriela Cavaglià. 2000. Integrating subject field codes into WordNet. In Proceedings of LREC-2000, Athens, Greece. find
10. Bernardo Magnini, Carlo Strapparava, Giovanni Pezzuli, and Alfio Gliozzo. 2001. Using domain information for word sense disambiguation. In Proceedings of the SENSEVAL -2 workshop, pages 111–114. find
11. Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll. 2004a. Finding predominant senses in untagged text. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain. find our card
12. Diana McCarthy, Rob Koeling, Julie Weeds, and John Carrolł. 2004b. Using automatically acquired predominant senses for word sense disambiguation. In Proceedings of the ACL SENSEVAL -3 workshop. find
13. Martha Palmer, Christiane Fellbaum, Scott Cotton, Lauren Delfs, and Hoa Trang Dang. 2001. English tasks: All-words and verb lexical sample. In Proceedings of the SENSEVAL -2 workshop, pages 21–24. find
14. Patrick Pantel and Dekang Lin. 2002. Discovering word senses from text. In Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 613–619, Edmonton, Canada. find
15. Siddharth Patwardhan and Ted Pedersen. 2003. The cpan wordnet::similarity package. http://search.cpan.org/author/SID/WordNet-Similarity-0.03/. ↗
16. Tony G. Rose, Mary Stevenson, and Miles Whitehead. 2002. The Reuters Corpus volume 1 - from yesterday’s news to tomorrow’s language resources. In Proc. of Third International Conference on Language Resources and Evaluation, Las Palmas de Gran Canaria. find
17. Yorick Wilks and Mark Stevenson. 1998. The grammar of sense: using part-of speech tags as a first step in semantic disambiguation. Natural Language Engineering, 4(2):135–143. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2004-mccarthy-automatic-identification-infrequent-word-senses/