Elamur Research⌕
☰
home / papers / 2002 / The Disambiguation of Nominalizations

The Disambiguation of Nominalizations

Paper · 2002 · Maria Lapata

Summary

The article addresses the automatic interpretation of nominalizations. These are noun compounds in which the head noun comes from a verb and the modifier fills one of that verb's argument slots, as in car lover. Lapata reduces the task to a binary choice: is the modifier the underlying subject or the direct object of the verb? The choice is treated as a disambiguation problem.

Such relations are never marked in text, so the model approximates them. It counts how often the modifier appears as subject or object of the head's source verb, using partial parsing of the British National Corpus. A log-likelihood ratio, the RA score, then compares the two readings. Many verb–noun pairs are unattested, so three smoothing methods are tested and combined. Contextual cues are added, and all evidence is merged with Ripper, a rule-learning system.

The best setup reaches 86.1% accuracy. The work shows that implicit compound semantics can be recovered statistically, and it sets a lower bound for harder compound-interpretation tasks.

Key points

  • Scope: only modifiers acting as subject or direct object of the nominalized verb. Prepositional-complement cases such as soccer competition are excluded.
  • The RA score is log₂ of P(obj | n1, n2) divided by P(subj | n1, n2). These probabilities are estimated from parsed verb–argument counts.
  • Data sparseness is handled with back-off smoothing, class-based smoothing and distance-weighted averaging. Combining the three outperforms using any one alone.
  • Context improves results. Ripper combining the probabilistic predictions with contextual features achieves 86.1% accuracy on the BNC, against a 61.5% baseline.
  • Ambiguous examples such as government promotion and satellite observation show that context can override a compound's default reading.

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

🎓University of EdinburghEdinburgh · United Kingdom359 works · 77,352 citations

 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

Cite

Cite as Maria Lapata. 2002. The Disambiguation of Nominalizations. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/089120102760276018

@article{lapata2002disambiguation,
  title = {{The Disambiguation of Nominalizations}},
  author = {Maria Lapata},
  journal = {Computational Linguistics},
  year = {2002},
  doi = {10.1162/089120102760276018},
  url = {https://doi.org/10.1162/089120102760276018}
}

References

50 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abney, Steve. 1996. “Partial parsing via finite-state cascades.” In John Carroll, editor, Workshop on Robust Parsing, pages 8–15, Prague. European Summer School in Logic, Language and Information, Prague. find
  2. Brown, Peter F., Vincent J. Della Pietra, Peter V. de Souza, and Robert L. Mercer. 1992. Class-based n-gram models of natural language. Computational Linguistics 18(4):467–479. find
  3. Burnage, Gavin. 1990. “Celex—A guide for users.” Technical Report, Centre for Lexical Information, University of Nijmegan, Nijmegan, Netherlands. find
  4. Burnard, Lou. 1995. Users Guide for the British National Corpus. British National Corpus Consortium, Oxford University Computing Service, Oxford. find
  5. Carletta, Jean. 1996. Agreement on classification tasks: The Kappa statistic. Computational Linguistics 22(2):249–254. find
  6. Carroll, John and Diana McCarthy. 2000. Word sense disambiguation using automatically acquired verbal preferences. Computers and the Humanities 34(1/2):109–114. find
  7. Church, Kenneth W. and William A. Gale. 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. Clark, Stephen and David Weir. 2001. “Class-based probability estimation using a semantic hierarchy.” In Proceedings of the Second North American Annual Meeting of the Association for Computational Linguistics, pages 95–102, Pittsburgh, Pennsylvania. find
  9. Cohen, William W. 1996. “Learning trees and rules with set-valued features.” In Proceedings of the 13th National Conference on Artificial Intelligence, pages 709–716, Portland, Oregon. AAAI Press, Menlo Park, California. find
  10. Collins, Michael and James Brooks. 1995. “Prepositional phrase attachment through a backed-off model.” In David Yarowsky and Kenneth W. Church, editors, Proceedings of the Third Workshop on Very Large Corpora, pages 27–38, Cambridge, Massachusetts.
  11. Copestake, Ann and Alex Lascarides. 1997. “Integrating symbolic and statistical representations: The lexicon pragmatics interface.” In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics, pages 136–143, Madrid, Spain. find
  12. Dagan, Ido, Lilian Lee, and Fernando C. N. Pereira. 1999. Similarity-based models of word cooccurrence probabilities. Machine Learning 34(1–3):43–69. find
  13. Downing, Pamela. 1977. On the creation and use of English compound nouns. Language 53(4):810–842. find
  14. Essen, Ute and Volker Steinbiss. 1992. “Co-occurrence smoothing for stochastic language modeling.” In Proceedings of International Conference on Acoustics Speech and Signal Processing, volume 1, pages 161–164, San Francisco, California. find
  15. Finin, Tim 1980. “The semantic interpretation of nominal compounds.” In Proceedings of First National Conference on Artificial Intelligence, pages 310–315, Stanford, California. AAAI Press, Menlo Park, California. find
  16. Grishman, Ralph and John Sterling. 1994. “Generalizing automatically generated selectional patterns.” In Proceedings of the 15th International Conference on Computational Linguistics, pages 742–747, Kyoto, Japan. find
  17. Hindle, Donald and Mats Rooth. 1993. Structural ambiguity and lexical relations. Computational Linguistics 19(1):103–120.
  18. Hirschberg, Julia, Diane Litman, and Marc Swerts. 2001. “Identifying user corrections automatically in spoken dialogue systems.” In Proceedings of the Second North American Annual Meeting of the Association for Computational Linguistics, pages 208–215, Pittsburgh, Pennsylvania. find
  19. Hobbs, Jerry R., Mark Stickel, Douglas Appelt, and Paul Martin. 1993. Interpretation as abduction. Journal of Artificial Intelligence 63(1–2):69–142. find
  20. Isabelle, Pierre. 1984. “Another look at nominal compounds.” In Proceedings of the 10th International Conference on Computational Linguistics and 22nd Annual Meeting of the Association for Computational Linguistics, pages 509–516, Stanford, California. find
  21. Jones, Bernard. 1995. “Predicating nominal compounds.” In Proceedings of the 17th Annual Conference of the Cognitive Science Society, pages 130–135, Pittsburgh, Pennsylvania. find
  22. 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 33(3):400–401. find
  23. Lakoff, George and Mark Johnson. 1980. Metaphors We Live By. University of Chicago Press, Chicago. find
  24. Lascarides, Alex and Alex Copestake. 1998. Pragmatics and word meaning. Journal of Linguistics 34(2):387–414. find
  25. Lauer, Mark. 1995. Designing Statistical Language Learners: Experiments on Compound Nouns. Ph.D. dissertation, Macquarie University, Sydney, Australia. find
  26. Lee, Lilian. 1999. “Measures of distributional similarity.” In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pages 25–32, College Park, Maryland.
  27. Lee, Lilian and Fernando Pereira. 1999. “Distributional similarity models: Clustering vs. nearest neighbors.” In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pages 33–40, College Park, Maryland. find
  28. Leonard, Rosemary. 1984. The Interpretation of English Noun Sequences on the Computer. North-Holland, Amsterdam. find
  29. Levi, Judith N. 1978. The Syntax and Semantics of Complex Nominals. Academic Press, New York. find
  30. Levin, Beth. 1993. English Verb Classes and Alternations: A Preliminary Investigation. University of Chicago Press, Chicago. find
  31. Li, Hang and Naoki Abe. 1998. Generalizing case frames using a thesaurus and the MDL principle. Computational Linguistics 24(2):217–244.
  32. Macleod, Catherine, Ralph Grishman, Adam Meyers, Leslie Barrett, and Ruth Reeves. 1998. “Nomlex: A lexicon of nominalizations.” In Proceedings of the Eighth International Congress of the European Association for Lexicography, pages 187–193, Liège, Belgium. find
  33. Marsh, Elaine. 1984. “A computational analysis of complex noun phrases in Navy messages.” In Proceedings of the 10th International Conference on Computational Linguistics, pages 505–508, Stanford, California. find
  34. McDonald, David. 1982. Understanding Noun Compounds. Ph.D. dissertation, Carnegie Mellon University, Pittsburgh, Pennsylvania. find
  35. Merlo, Paola and Suzanne Stevenson. 1999. “Automatic verb classification using distributions of grammatical features.” In Proceedings of the Ninth Conference of the European Chapter of the Association for Computational Linguistics, pages 45–51, Bergen, Norway. find
  36. Miller, George A., Richard Beckwith, Christiane Fellbaum, Derek Gross, and Katherine J. Miller. 1990. Introduction to WordNet: An on-line lexical database. International Journal of Lexicography 3(4):235–244. find
  37. Mosteller, Frederick and David L. Wallace. 1964. Inference and Disputed Authorship: The Federalist. Addison-Wesley, London. find
  38. Passonneau, Rebecca J. and Diane J. Litman. 1997. Discourse segmentation by human and automated means. Computational Linguistics 23(1):103–140.
  39. Pedersen, Ted. 2001. “A decision tree of bigrams is an accurate predictor of word sense.” In Proceedings of the Second North American Annual Meeting of the Association for Computational Linguistics, pages 79–86, Pittsburgh, Pennsylvania. find
  40. Pereira, Fernando, Naftali Tishby, and Lillian Lee. 1993. “Distributional clustering of English words.” In Proceedings of the 31st Annual Meeting of the Association for Computational Linguistics, pages 183–190, Columbus, Ohio.
  41. Quirk, Randolph, Sidney Greenbaum, Geoffrey Leech, and Jan Svartvik. 1985. A Comprehensive Grammar of the English Language. Longman, London. find
  42. Resnik, Philip Stuart. 1993. Selection and Information: A Class-Based Approach to Lexical Relationships. Ph.D. dissertation, University of Pennsylvania, Philadelphia. find
  43. Selkirk, Elizabeth. 1982. The Syntax of Words. MIT Press, Cambridge, Massachusetts. find
  44. Siegel, Eric V. 1999. “Corpus-based linguistic indicators for aspectual classification.” In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pages 112–119, College Park, Maryland. find
  45. Siegel, Eric V. and Kathleen R. McKeown. 1994. “Emergent linguistic rules from inducing decision trees: Disambiguating discourse clue words.” In Proceedings of the 12th National Conference on Artificial Intelligence, pages 820–826, Seattle, Washington. AAAI Press, Menlo Park, California. find
  46. Siegel, Sidney and N. John Castellan. 1988. Nonparametric Statistics for the Behavioral Sciences. McGraw-Hill, New York. find
  47. Sparck Jones, Karen. 1983. “Compound noun interpretation problems.” Technical Report 45, Computer Laboratory, Cambridge University, Cambridge, England. find
  48. Vanderwende, Lucy. 1994. “Algorithm for automatic interpretation of noun sequences.” In Proceedings of the 15th International Conference on Computational Linguistics, pages 782–788, Kyoto, Japan. find
  49. Warren, Beatrice. 1978. Semantic Patterns of Noun-Noun Compounds. Acta Universitatis Gothoburgensis, Göteborg, Sweden. find
  50. Wu, Dekai. 1993. “Approximating maximum-entropy ratings for evidential parsing and semantic interpretation.” In Proceedings of 13th International Joint Conference on Artificial Intelligence, pages 1290–1296, Chamberry, France. Morgan Kaufmann. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lapata-2002-disambiguation-nominalizations/