Classifying the Semantic Relations in Noun Compounds via a Domain-Specific Lexical Hierarchy

What it is about

The paper classifies the semantic relation inside a two-word noun compound in biomedical text, for example treatment-for-disease in "migraine treatment". The authors define 38 relations by iterative refinement over the compounds. Each noun is mapped to a MeSH term through UMLS, so the hierarchy gives a category for a noun the training data has never seen. The data holds 2,245 compounds whose two nouns both map to MeSH. A neural network with one-of-eighteen output reaches up to 62% accuracy. The test that matters is the unseen-word case: training on the hierarchy generalises better than a baseline that uses the words themselves, and the paper reports strong results on compounds whose words are not in the training set.

Ideas

• I1. A WordNet analogue in onto: map each noun to its hypernym chain at a chosen depth, as the paper maps to MeSH, and classify relations by a counted table with back-off. Measure: accuracy on held-out EWT compounds whose nouns are absent from training, against the word-only baseline.
• I2. Split every test set by word: report accuracy on seen and on unseen nouns. The paper's main claim rests on this split, so en folds should report it too.
• I3. Relation labels as a prag role on the compound, with the chosen relation given with its reason from the hierarchy. Measure: the share of labels with a stated reason on EWT, and the agreer's rejection rate on a hand-checked sample.

For Mova

The chapter is 18. Compounding, conversion and the minor processes. The code is onto/src/wsd.rs (the hierarchy, as an explained choice) and world/src/frames.rs for the relations. The paper's data is biomedical, so it does not fit general English; it is not Mova data, and any figure must come from EWT test.

Cite

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

@inproceedings{rosario2001classifying,
  title = {{Classifying the Semantic Relations in Noun Compounds via a Domain-Specific Lexical Hierarchy}},
  author = {Rosario, Barbara and Hearst, Marti},
  booktitle = {Proceedings of the 2001 Conference on Empirical Methods in Natural Language Processing},
  year = {2001},
  url = {https://aclanthology.org/W01-0511/}
}

References

29 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eric Brill and Philip Resnik. 1994. A rule-based approach to prepositional phrase attachment dis-amibuation. In Proceedings of COLING-94. find
2. Claire Cardie. 1997. Empirical methods in information extraction. AI Magazine, 18(4). find
3. Douglass R. Cutting, Julian Kupiec, Jan O. Pedersen, and Penelope Sibun. 1991. A practical part-of-speech tagger. In The 3rd Conference on Applied Natural Language Processing, Trento, Italy. find
4. P. Downing. 1977. On the creation and use of english compound nouns. Language, (53):810–842. find
5. Christiane Fellbaum, editor. 1998. WordNet: An Electronic Lexical Database. MIT Press. find
6. Timothy W. Finin. 1980. The Semantic Interpretation of Compound Nominals. Ph.d. dissertation, University of Illinois, Urbana, Illinois. find
7. Marti A. Hearst. 1990. A hybrid approach to restricted text interpretation. In Paul S. Jacobs, editor, Text-Based Intelligent Systems: Current Research in Text Analysis, Information Extraction, and Retrieval, pages 38–43. GE Research & Development Center, TR 90CRD198. find
8. Donald Hindle and Mats Rooth. 1993. Structual ambiguity and lexical relations. Computational Linguistics, 19(1). find
9. Jerry R. Hobbs, Mark Stickel, Douglas Appelt, and Paul Martin. 1993. Interpretation as abduction. Artificial Intelligence, 63(1-2). find
10. L. Humphreys, D.A.B. Lindberg, H.M. Schoolman, and G. O. Barnett. 1998. The unified medical language system: An informatics research collaboration. Journal of the American Medical Informatics Assocation, 5(1):1–13. find
11. Maria Lapata. 2000. The automatic interpretation of nominalizations. In AAAI Proceedings. find
12. Mark Lauer and Mark Dras. 1994. A probabilistic model of compound nouns. In Proceedings of the 7th Australian Joint Conference on AI. find
13. Mark Lauer. 1995. Corpus statistics meet the compound noun. In Proceedings of the 33rd Meeting of the Association for Computational Linguistics, June. find
14. Judith Levi. 1978. The Syntax and Semantics of Complex Nominals. Academic Press, New York. find
15. Hang Li and Naoki Abe. 1998. Generalizing case frames using a thesaurus and the MDI principle. Computational Linguistics, 24(2):217–244. find
16. Mark Liberman and Richard Sproat. 1992. The stress and structure of modified noun phrases in english. In I.l Sag and A. Szabolsci, editors, Lexical Matters. CSLI Lecture Notes No. 24, University of Chicago Press. find
17. Henry J. Lowe and G. Octo Barnett. 1994. Understanding and using the medical subject headings (MeSH) vocabulary to perform literature searches. Journal of the American Medical Assocation (JAMA), 271(4):1103–1108. find
18. Hwee Tou Ng and John Zelle. 1997. Corpus-based approaches to semantic interpretation in natural language processing. AI Magazine, 18(4). find
19. James Pustejovsky, Sabine Bergler, and Peter Anick. 1993. Lexical semantic techniques for corpus analysis. Computational Linguistics, 19(2). find
20. Philip Resnik and Marti A. Hearst. 1993. Structural ambiguity and conceptual relations. In Proceedings of the ACL Workshop on Very Large Corpora, Columbus, OH. find
21. Philip Resnik. 1993. Selection and Information: A Class-Based Approach to Lexical Relationships. Ph.D. thesis, University of Pennsylvania, December. (Institute for Research in Cognitive Science report IRCS-93-42). find
22. Philip Resnik. 1995. Disambiguating noun groupings with respect to WordNet senses. In Third Workshop on Very Large Corpora. Association for Computational Linguistics. find
23. Ellen Riloff. 1996. Automatically generating extraction patterns from untagged text. In Proceedings of the Thirteenth National Conference on Artificial Intelligence and the Eighth Innovative Applications of Artificial Intelligence Conference, Menlo Park. AAAI Press / MIT Press. find
24. Thomas Rindflesch, Lorraine Tanabe, John N. Weinstein, and Lawrence Hunter. 2000. Extraction of drugs, genes and relations from the biomedical literature. Pacific Symposium on Biocomputing, 5(5). find
25. Don R. Swanson and N. R. Smalheiser. 1994. Assessing a gap in the biomedical literature: Magnesium deficiency and neurologic disease. Neuroscience Research Communications, 15:1–9. find
26. Len Talmy. 1985. Force dynamics in language and thought. In Parasession on Causatives and Agentivity, University of Chicago. Chicago Linguistic Society (21st Regional Meeting). find
27. Lucy Vanderwende. 1994. Algorithm for automatic interpretation of noun sequences. In Proceedings of COLING-94, pages 782–788. find
28. V. Vapnik. 1998. Statistical Learning Theory. Oxford University Press. find
29. Beatrice Warren. 1978. Semantic Patterns of Noun-Noun Compounds. Acta Universitatis Gothoburgensis. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2001-rosario-classifying-semantic-relations-noun-compounds/