Elamur Research⌕
☰
home / papers / 1994 / Word Sense Disambiguation Using a Second Language Monolingual Corpus

Word Sense Disambiguation Using a Second Language Monolingual Corpus

Summary

The paper addresses lexical ambiguity, focusing on target word selection in machine translation: picking the right target-language equivalent for an ambiguous source word. Sense-tagged corpora are costly to build, so the authors use a plain monolingual corpus in the target language. Languages divide meanings among words differently, so each candidate translation acts as a separate "sense" whose co-occurrence statistics can be counted without manual tagging. A source-language parser (McCord's Slot Grammars) finds syntactic relations such as verb-object and subject-verb. A bilingual lexicon then maps every relation to its possible target-language versions. Frequencies of those versions in a parsed target corpus decide the choice. A statistical confidence model declines to choose when no candidate clearly wins, and a constraint propagation algorithm resolves all ambiguities in a sentence jointly. On randomly chosen Hebrew news sentences translated into English, the method made a decision for most ambiguous words and was usually right. It clearly beat a baseline that uses only prior word frequencies. This shows that cheap monolingual data can replace hand-built semantic knowledge.

Key points

  • Evaluation used three example sets of Hebrew and German source text. The Hebrew–English set came from foreign news sections of Israeli newspapers, such as Ha-Aretz.
  • On the Hebrew–English set, the model applied to 70% of ambiguous words and chose correctly in 91% of those cases.
  • A later, weaker variant (Dagan, Marcus, and Markovitch 1993) used window-based co-occurrence instead of a target parser. It reached 85% precision on computer-domain texts (a software manual).
  • In the motivating example, the target corpus contained "peace treaty" 49 times and "peace contract" never. "Sign a treaty" appeared 79 times, while each competing verb appeared at most twice. The correct choices were not the most frequent words overall.
  • The authors estimate that a target corpus of a few hundred thousand words should be enough for a well-defined domain. Unlike parallel-corpus approaches, the method needs no bilingual corpus.

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

Fields: Natural language processing

Topics Word sense disambiguation Grammatical error correction & learner language

Institutions

🏢AT&TBedminster · United States19 works · 12,873 citations🎓Technion – Israel Institute of TechnologyHaifa · Israel20 works · 3,844 citations

Cite

Cite as Ido Dagan and Alon Itai. 1994. Word Sense Disambiguation Using a Second Language Monolingual Corpus. Computational Linguistics.

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

@article{dagan1994word,
  title = {{Word Sense Disambiguation Using a Second Language Monolingual Corpus}},
  author = {Ido Dagan and Alon Itai},
  journal = {Computational Linguistics},
  year = {1994},
  url = {https://aclanthology.org/J94-4003/}
}

References

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

  1. Agresti, Alan (1990). Categorical Data Analysis. New York: John Wiley & Sons. find
  2. Alcalay, R. (1990). The Complete Hebrew-English Dictionary. Massada. find
  3. Brown, P.; Cocke, J.; Della Pietra, S.; Della Pietra, V.; Jelinek, E; Mercer, R. L.; and Roossin, P. C. (1990). A statistical approach to language translation. Computational Linguistics 16(2):79-85. our card
  4. Brown, P.; Della Pietra, S.; Della Pietra, V.; and Mercer, R. (1991). "Word sense disambiguation using statistical methods." In Proceedings, Annual Meeting of the Association for Computational Linguistics, 264-270. our card
  5. Brown, Peter; Della Pietra, Stephen; Della Pietra, Vincent; and Mercer, Robert (1993). "But dictionaries are data too." In Proceedings, ARPA Workshop on Human Language Technology, 202-205. find
  6. Chodorow, M. S.; Byrd, R. J.; and Heidron, G. E. (1985). "Extracting semantic hierarchies from a large on-line dictionary." In Proceedings, Annual Meeting of the Association for Computational Linguistics, 299-304. find
  7. Church, Kenneth W., and Gale, William A. (1991). "A comparison of the enhanced Good-Turing and deleted estimation methods for estimating probabilities of English bigrams." Computer Speech and Language 5:19-54. find
  8. Church, Kenneth W., and Hanks, Patrick (1990). "Word association norms, mutual information, and lexicography." Computational Linguistics 16(1):22-29. our card
  9. Dagan, Ido; Church, Kenneth; and Gale, William (1993). "Robust bilingual word alignment for machine aided translation." In Proceedings, Workshop on Very Large Corpora: Academic and Industrial Perspectives, 1-8. find
  10. Dagan, Ido, and Itai, Alon (1990). "Automatic acquisition of constraints for the resolution of anaphora references and syntactic ambiguities." In Proceedings, International Conference on Computational Lf::,ouistics, Volume 3, 330-332. find
  11. Dagan, Ido, and Itai, Alon (1991). "A statistical filter for resolving pronoun references." In Artificial Intelligence and Computer Vision (Proceedings, 7th Israeli Symposium on Artificial Intelligence and Computer Vision, 1990), edited by Y. A. Feldman and A. Bruckstein, 125-135. Elsevier Science P… find
  12. Dagan, Ido; Itai, Alon; and Schwall, Ulrike (1991). "Two languages are more informative than one." In Proceedings, Annual Meeting of the Association for Computational Linguistics, 130-137. find
  13. Dagan, Ido; Marcus, Shaul; and Markovitch, Shaul (1993). "Contextual word similarity and estimation from sparse data." In Proceedings, Annual Meeting of the Association for Computational Linguistics, 164-171. find
  14. Gale, William; Church, Kenneth; and Yarowsky, David (1992a). "Using bilingual materials to develop word sense disambiguation methods." In Proceedings, International Conference on Theoretical and Methodolgical Issues in Machine Translation, 101-112. find
  15. Gale, William; Church, Kenneth; and Yarowsky, David (1992b). "Work on statistcal methods for word sense disambiguation." In Working Notes, AAAI Fall Symposium Series, Probabilistic Approaches to Natural Language, 54-60. find
  16. Gale, William; Church, Kenneth; and Yarowsky, David (1993). "A method for disambiguating word senses in a large corpus." Computers and the Humanities 26:415-439. find
  17. Golan, Igal; Lappin, Shalom; and Rimon, Mori (1988). "An active bilingual lexicon for machine translation." In Proceedings, Conference on Computational Linguistics, 205-211. find
  18. Grishman, R.; Hirschman, L.; and Thanh Nhan, Ngo (1986). "Discovery procedures for sublanguage selectional patterns - initial experiments." Computational Linguistics 12:205-214. find
  19. Hearst, Marti (1991). "Noun homograph disambiguation using local context in large text corpora." In Proceedings, Annual Conference of the UW Center for the New OED and Text Research, 1-22. find
  20. Hindle, D. (1990). "Noun classification from predicate-argument structures." In Proceedings, Annual Meeting of the Association for Computational Linguistics, 268-275. our card
  21. Hindle, D., and Rooth, M. (1991). "Structural ambiguity and lexical relations." In Proceedings, Annual Meeting of the Association for Computational Linguistics, 229-236. our card
  22. Hornby, A. S.; Ruse, C.; Reif, J. A.; and Levy, Y. (1986). Oxford Student's Dictionary for Hebrew Speakers. Kernerman Publishing Ltd., Lonnie Kahn & Co. Ltd. find
  23. Jelinek, Frederick (1990). "Self-organized language modeling for speech recognition." In Readings in Speech Recognition, edited by Alex Waibel and Kai-Fu Lee, 450-506. San Mateo, California: Morgan Kaufmann Publishers, Inc. find
  24. Jelinek, Frederick; Mercer, Robert L.; and Roukos, Salim (1992). "Principles of lexical language modeling for speech recognition." In Advances in Speech Signal Processing, edited by Sadaoki Furui and M. Mohan Sondhi, 651-699. Mercer Dekker, Inc. find
  25. Katz, Slava M. (1987). "Estimation of probabilities from sparse data for the language model component of a speech recognizer." IEEE Transactions on Acoustics, Speech, and Signal Processing 35(3):400-401. find
  26. Lenat, D. B.; Guha, R. V.; Pittman, K.; Pratt, D.; and Shepherd, M. (1990). "Cyc: Toward programs with common sense." Communications of the ACM 33(8):30-49. find
  27. McCord, M. C. (1990). "Slot grammar: A system for simpler construction of practical natural language grammars." In Natural Language and Logic: International Scientific Symposium. Lecture Notes in Computer Science, edited by R. Studer, 118-145. Berlin: Springer Verlag. find
  28. McCord, M. C. (1991). "The slot grammar system." Technical report RC 17313, IBM Research Report. In Unification in Grammar, edited by J. Wedekind and C. Rohrer, in press. Cambridge, MA: MIT Press. find
  29. McRoy, Susan W. (1992). "Using multiple knowledge sources for word sense disambiguation." Computational Linguistics 18(1):1-30. find
  30. Miller, L. Chris. (1993). "Bableware for the desktop." BYTE January:177-183. find
  31. Mosteller, Frederick, and Wallace, David (1964). Inference and Disputed Authorship: The Federalist. Readifig, Massachusetts: Addison-Wesley. find
  32. National Language Research Institute (1964). Bunrui Goi Hyou (Word List by Semantic Principles). Shuuel Publishing. find
  33. Nirenburg, S., editor (1987). Machine Translation. Cambridge: Cambridge University Press. find
  34. Nirenburg, S.; Monarch, I.; Kaufmann, T.; Nirenburg, I.; and Carbonell, J. (1988). "Acquisition of very large knowledge bases: Methodology, tools and applications." Technical report CMU-CMT-88-108, Center for Machine Translation, Carnegie-Mellon. find
  35. Sadler, V. (1989). Working with Analogical Semantics: Disambiguation Techniques in DLT. Foris Publications. find
  36. Schfitze, Hinrich (1992a). "Context space." In Working Notes, AAAI Fall Symposium on Probabilistic Approaches to Natural Language. find
  37. Schiitze, Hinrich (1992). "Dimensions of meaning." In Proceedings, Supercomputing, 787-796. find
  38. Schfitze, Hinrich (1993). "Word space." In Advances in Neural Information Processing Systems 5, edited by S. J. Hanson, J. D. Cowan, and C. L. Giles, 895-902. San Mateo, California: Morgan Kaufman Publishers. find
  39. Simpson, Greg B., and Burgess, Curt (1988). "Implications of lexical ambiguity resolution for word recognition." In Lexical Ambiguity Resolution, edited by G. W. Cotrell, S. L. Small, and M. K. Tanenhaus, 271-288. San Mateo, California: Morgan Kaufman Publishers. find
  40. Smadja, Frank (1993). "Retrieving collocations from text: Xtract." Computational Linguistics 19(1):143-177. our card
  41. Woods, W. A. (1973). "An experimental parsing system for transition network grammars." In Natural Language Processing, edited by R. Rustin, 111-154. Algorithmics Press. find
  42. Yarowsky, David (1992). "Word sense disambiguation using statistical models of Roget's categories trained on large corpora." In Proceedings, International Conference on Computational Linguistics, 454-460. our card
  43. Zernik, U., and Jacobs, P. (1990). "Tagging for learning: Collecting thematic relations from corpus." In Proceedings, International Conference on Computational Linguistics, Volume 1, 34-39. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/dagan-1994-word-sense-disambiguation-second-language/