Elamur Research⌕
☰
home / papers / 1998 / Selective Sampling for Example-based Word Sense Disambiguation

Selective Sampling for Example-based Word Sense Disambiguation

Paper · 1998 · Atsushi Fujii, Kentaro Inui, Takenobu Tokunaga et al.

Summary

Example-based word sense disambiguation systems choose a verb's sense by finding the most similar stored example. Building a useful example database is costly in two ways. Every example must be labelled by hand ("overhead for supervision"), and searching a very large database is slow ("overhead for search"). Fujii and colleagues address both costs with selective sampling for Japanese verb sense disambiguation. Their system follows the nearest-neighbour method of Kurohashi and Nagao (1994) and adds the case contribution weighting (CCD) of Fujii et al. (1996). Verb senses and seed case fillers come from the IPAL dictionary.

The system does not label everything. It alternates between two steps:

  • disambiguating unlabelled examples, and
  • asking a human to label only those with the highest "training utility," meaning how much an example would help interpret the remaining unlabelled data.

In experiments on roughly a thousand sentences, this approach needed fewer labelled examples and produced a smaller database than other sampling strategies, with no loss in accuracy. The work shows how active learning can be adapted to memory-based NLP.

Key points

  • A preliminary study on eleven polysemous Japanese verbs showed that accuracy rises with more labelled data. Reaching over 80% accuracy required on the order of a hundred labelled examples per verb.
  • Senses are scored by case-filler similarity, for example nominative ga and accusative wo. CCD gives more weight to cases whose fillers better separate the senses, such as the accusative for the verb toru.
  • The core criterion, training utility, considers both how uncertain the system is about an example and how labelling it would affect other unlabelled examples.
  • The method is compared with committee-based sampling (Engelson and Dagan 1996) and uncertainty sampling (Lewis and Gale 1994). Both were originally designed for statistical models.
  • Labelled samples are added directly to the database without re-estimating parameters. Because of this, the database stays as informative as possible for its size whenever sampling is stopped.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Tokyo Institute of TechnologyTokyo · Japan22 works · 2,137 citations

Also on the byline: Kyushu Institute of Technology.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Word sense disambiguation · 83 works

Cite

Cite as Atsushi Fujii, Kentaro Inui, Takenobu Tokunaga and Hozumi Tanaka. 1998. Selective Sampling for Example-based Word Sense Disambiguation. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

@article{fujii1998selective,
  title = {{Selective Sampling for Example-based Word Sense Disambiguation}},
  author = {Atsushi Fujii, Kentaro Inui, Takenobu Tokunaga and Hozumi Tanaka},
  journal = {Computational Linguistics},
  year = {1998},
  url = {https://aclanthology.org/J98-4002/}
}

References

61 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Aha, David W., Dennis Kibler, and Marc K. Albert. 1991. Instance-based learning algorithms. Machine Learning, 6(1):37-66.
  2. Brown, Peter E, Stephen A. Della Pietra, and Vincent J. Della Pietra. 1991. Word-sense disambiguation using statistical methods. In Proceedings of the 29th Annual Meeting, pages 264-270, Association for Computational Linguistics.
  3. Bruce, Rebecca and Janyce Wiebe. 1994. Word-sense disambiguation using decomposable models. In Proceedings of the 32nd Annual Meeting, pages 139-146, Association for Computational Linguistics. find
  4. Chapman, Robert L. 1984. Roget's International Thesaurus. Fourth Edition. Harper and Row. find
  5. Charniak, Eugene. 1993. Statistical Language Learning. MIT Press, Cambridge, MA. find
  6. Cohn, David, Les Atlas, and Richard Ladner. 1994. Improving generalization with active learning. Machine Learning, 15(2):201-221. find
  7. Dagan, Ido and Alon Itai. 1994. Word sense disambiguation using a second language monolingual corpus. Computational Linguistics, 20(4):563-596.
  8. Engelson, Sean P. and Ido Dagan. 1996. Minimizing manual annotation cost in supervised training from corpora. In Proceedings of the 34th Annual Meeting, pages 319-326, Association for Computational Linguistics. find
  9. Frakes, William B. and Ricardo Baeza-Yates. 1992. Information Retrieval: Data Structure & Algorithms. PTR Prentice-Hall. find
  10. Fujii, Atsushi, Kentaro Inui, Takenobu Tokunaga, and Hozumi Tanaka. 1996. To what extent does case contribute to verb sense disambiguation? In Proceedings of the 16th International Conference on Computational Linguistics, pages 59-64. find
  11. Fukumoto, Fumiyo and Jun'ichi Tsujii. 1994. Automatic recognition of verbal polysemy. In Proceedings of the 15th International Conference on Computational Linguistics, pages 764-768. find
  12. Gale, William, Kenneth Ward Church, and David Yarowsky. 1992. Estimating upper and lower bounds on the performance of word-sense disambiguation programs. In Proceedings of the 30th Annual Meeting, pages 249-256, Association for Computational Linguistics. find
  13. Gale, William, Kenneth Ward Church, and David Yarowsky. 1993. A method for disambiguating word senses in a large corpus. Computers and the Humanities, 26:415-439. find
  14. Guthrie, Joe A., Louise Guthrie, Yorick Wilks, and Homa Aidinejad. 1991. Subject-dependent co-occurrence and word sense disambiguation. In Proceedings of the 29th Annual Meeting, pages 146-152, Association for Computational Linguistics. find
  15. Hearst, Marti A. 1991. Noun homograph disambiguation using local context in large text corpora. In Proceedings of the 7th Annual Conference of the University of Waterloo Centre for the New OED and Text Research, pages 1-22. find
  16. Hindle, Donald. 1990. Noun classification from predicate-argument structures. In Proceedings of the 28th Annual Meeting, pages 268-275, Association for Computational Linguistics.
  17. Hirst, Graeme. 1987. Semantic Interpretation and the Resolution of Ambiguity. Cambridge University Press. find
  18. Information-technology Promotion Agency. 1987. IPAL Japanese dictionary for computers (basic verbs) (in Japanese). find
  19. Japan Electronic Dictionary Research Institute. 1995. EDR electronic dictionary technical guide (in Japanese). find
  20. Kaji, Hiroyuki, Yuuko Kida, and Yasutsugu Morimoto. 1992. Learning translation templates from bilingual text. In Proceedings of the 14th International Conference on Computational Linguistics, pages 672-678. find
  21. Kameda, Masayuki. 1996. A portable & quick Japanese parser: QJP. In Proceedings of the 16th International Conference on Computational Linguistics, pages 616-621. find
  22. Karov, Yael and Shimon Edelman. 1996. Learning similarity-based word sense disambiguation. In Proceedings of the 4th Workshop on Very Large Corpora, pages 42-55. find
  23. Krovets, Robert and W. Bruce Croft. 1992. find
  24. Lexical ambiguity and information retrieval. ACM Transactions on Information Systems, 10(2):115-141. find
  25. Kurohashi, Sadao and Makoto Nagao. 1994. A method of case structure analysis for Japanese sentences based on examples in case frame dictionary. IEICE Transactions on Information and Systems, E77-D(2):227-239. find
  26. Leacock, Claudia, Geoffrey Towell, and Ellen Voorhees. 1993. Corpus-based statistical sense resolution. In Proceedings of ARPA Human Language Technology Workshop, pages 260-265. find
  27. Lewis, David D. and William Gale. 1994. A sequential algorithm for training text classifiers. In Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 3-12. find
  28. Li, Xiaobin, Stan Szpakowicz, and Stan Matwin. 1995. A WordNet-based algorithm for word sense disambiguation. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, pages 1368-1374. find
  29. Lytinen, Steven L. 1986. Dynamically combining syntax and semantics in natural language processing. In Proceedings of AAAI-86, pages 574-578. find
  30. Mainichi Shimbun. 1991-1994. Mainichi shimbun CD-ROM '91-'94 (in Japanese). find
  31. Matsumoto, Yuji, Sadao Kurohashi, Takehito Utsuro, Yutaka Myoki, and Makoto Nagao, 1993. JUMAN Users Manual (in Japanese). Kyoto University and Nara Institute of Science and Technology. find
  32. Miller, George A., Richard Beckwith, Christiane Fellbaum, Derek Gross, Katherine Miller, and Randee Tengi. 1993. Five papers on WordNet. Technical Report CLS-Rep-43, Cognitive Science Laboratory, Princeton University. find
  33. Mooney, Raymond J. 1996. Comparative experiments on disambiguating word senses: An illustration of the role of bias in machine learning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 82-91. find
  34. Nagao, Katashi. 1994. A preferential constraint satisfaction technique for natural language analysis. IEICE Transactions on Information and Systems, E77-D(2):161-170. find
  35. Nagao, Makoto. 1984. A framework of a mechanical translation between Japanese and English by analogy principle. ArtiJicial and Human Intelligence, pages 173-180. find
  36. Nasukawa, Tetsuya. 1993. Discourse constraint in computer manuals. In Proceedings of the 5th International Conference on Theoretical and Methodological Issues in Machine Translation, pages 183-194. find
  37. National Language Research Institute. 1964. Bunruigoihyo (in Japanese). Shuei publisher. find
  38. Ng, Hwee Tou. 1997. Exemplar-based word sense disambiguation: Some recent improvements. In Proceedings of the 2nd Conference on Empirical Methods in Natural Language Processing, pages 208-213. find
  39. Ng, Hwee Tou and Hian Beng Lee. 1996. Integrating multiple knowledge sources to disambiguate word sense: An exemplar-based approach. In Proceedings of the 34th Annual Meeting, pages 40-47, Association for Computational Linguistics.
  40. Niwa, Yoshiki and Yoshihiko Nitta. 1994. Co-occurrence vectors from corpora vs. distance vectors from dictionaries. In Proceedings of the 15th International Conference on Computational Linguistics, pages 304-309. find
  41. Nomiyama, Hiroshi. 1993. Machine translation by case generalization (in Japanese). Transactions of Information Processing Society of Japan, 34(5):905-912. find
  42. Pedersen, Ted, Rebecca Bruce, and Janyce Wiebe. 1997. Sequential model selection for word sense disambiguation. In Proceedings of the 5th Conference on Applied Natural Language Processing, pages 388-395. find
  43. Pustejovsky, James and Branimir Boguraev. 1993. Lexical knowledge representation and natural language processing. Artificial Intelligence, 63(1-2):193-223. find
  44. Real World Computing Partnership. 1995. RWC text database (in Japanese). find
  45. Resnik, Philip. 1993. Selection and Information: A Class-Based Approach to Lexical Relationships. Ph.D. thesis, University of Pennsylvania. find
  46. Ribas, Francesc. 1995. On learning more appropriate selectional restrictions. In Proceedings of the 7th Conference of the European Chapter of the Association for Computational Linguistics, pages 112-118. find
  47. Salton, Gerard and Michael J. McGill. 1983. find
  48. Introduction to Modern Information Retrieval. McGraw-Hill. find
  49. Schiitze, Hinrich. 1992. Dimensions of meaning. In Proceedings of Supercomputing, pages 787-796. find
  50. Seung, H. S., M. Opper, and H. Sompolinsky. 1992. Query by committee. In Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, pages 287-294. find
  51. Smyth, Barry and Mark T. Keane. 1995. Remembering to forget: A competence-preserving case deletion policy for case-based reasoning systems. find
  52. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, pages 377-382. find
  53. Tokunaga, Takenobu, Makoto Iwayama, and Hozumi Tanaka. 1995. Automatic thesaurus construction based on grammatical relations. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, pages 1308-1313. find
  54. Uramoto, Naohiko. 1994a. A best-match algorithm for broad-coverage example-based disambiguation, hi Proceedings of the 15th International Conference on Computational Linguistics, pages 717-721. find
  55. Uramoto, Naohiko. 1994b. Example-based word-sense disambiguation. IEICE Transactions on Information and Systems, E77-D(2):240-246. find
  56. Utsuro, Takehito. 1996. Sense classification of verbal polysemy based on bilingual class/class association. In Proceedings of the 16th International Conference on Computational Linguistics, pages 968-973. find
  57. Utsuro, Takehito, Kiyotaka Uchimoto, Mitsutaka Matsumoto, and Makoto Nagao. 1994. Thesaurus-based efficient example retrieval by generating retrieval queries from similarities. In Proceedings of the 15th International Conference on Computational Linguistics, pages 1044-1048. find
  58. Voorhees, Ellen M. 1993. Using WordNet to disambiguate word senses for text retrieval. In Proceedings of the 16th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 171-180. find
  59. Yarowsky, David. 1992. Word-sense disambiguation using statistical models of Roget's categories trained on large corpora. In Proceedings of the 14th International Conference on Computational Linguistics, pages 454-460.
  60. Yarowsky, David. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd Annual Meeting, pages 189-196, Association for Computational Linguistics.
  61. Zernik, Uri. 1989. Lexicon acquisition: Learning from corpus by capitalizing on lexical categories. In Proceedings of the 11th International Joint Conference on Artificial Intelligence, pages 1556-1562. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/fujii-1998-selective-sampling-example-based-word/