Elamur Research⌕
☰
home / papers / 2001 / Automatic Verb Classification Based on Statistical Distributions of Argument Structure

Automatic Verb Classification Based on Statistical Distributions of Argument Structure

Paper · 2001 · Paola Merlo and Suzanne Stevenson

Summary

Verbs carry most of a sentence's relational meaning, so NLP systems need lexical knowledge about how verbs link participants to events. Merlo and Stevenson study whether this knowledge can be learned from corpora. They focus on three classes of English verbs that can be used with or without an object: unergative, unaccusative, and object-drop. All three allow the same subcategorization frames, so syntax alone cannot separate them. What differs is the thematic roles each class gives to subject and object.

From this linguistic analysis, the authors derive five numerical indicators that approximate semantic properties, such as causativity or subject animacy, through countable syntactic patterns. They extract these indicators from large syntactically annotated corpora and use them to train a supervised classifier. The classifier assigns one predominant class to each verb type, including verbs absent from training. Accuracy reaches 69.8%, well above chance and approaching expert performance. The work shows that deep linguistic insight, encoded in feature design, can be combined with scalable statistical learning.

Key points

  • The task is a three-way classification of optionally intransitive English verbs (unergative, unaccusative, object-drop), which share subcategorization frames but differ in thematic role assignment.
  • Accuracy is 69.8%, against a chance baseline of 33.9% and an expert-based upper bound of 86.5%.
  • This is a 54% error-rate reduction over chance, or 68% when measured relative to the human expert ceiling.
  • Only five linguistically motivated features are used, all automatically extractable from annotated text despite noise from tagging errors and imperfect extraction patterns.
  • Classification works at the level of verb types, so new verbs can be labeled. Handling ambiguous individual tokens and intersective Levin classes is left for future work.

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 TorontoToronto · Canada47 works · 50,254 citations🎓University of GenevaGeneva · Switzerland23 works · 2,820 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

Cite

Cite as Paola Merlo and Suzanne Stevenson. 2001. Automatic Verb Classification Based on Statistical Distributions of Argument Structure. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/089120101317066122

@article{merlo2001automatic,
  title = {{Automatic Verb Classification Based on Statistical Distributions of Argument Structure}},
  author = {Paola Merlo and Suzanne Stevenson},
  journal = {Computational Linguistics},
  year = {2001},
  doi = {10.1162/089120101317066122},
  url = {https://doi.org/10.1162/089120101317066122}
}

References

62 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abney, Steven. 1996. Partial parsing via finite-state cascades. In John Carroll, editor, Proceedings of the Workshop on Robust Parsing at the Eighth Summer School on Logic, Language and Information, number 435 in CSRP, pages 8-15. University of Sussex, Brighton. find
  2. Aone, Chinatsu and Douglas McKee. 1996. Acquiring predicate-argument mapping information in multilingual texts. In Branimir Boguraev and James Pustejovsky, editors, Corpus Processing for Lexical Acquisition. MIT Press, pages 191-202. find
  3. Basili, Roberto, Maria-Teresa Pazienza, and Paola Velardi. 1996. A context-driven conceptual clustering method for verb classification. In Branimir Boguraev and James Pustejovsky, editors, Corpus Processing for Lexical Acquisition. MIT Press, pages 117-142. find
  4. Boguraev, Branimir and Ted Briscoe. 1989. Utilising the LDOCE grammar codes. In Branimir Boguraev and Ted Briscoe, editors, Computational Lexicography for Natural Language Processing. Longman, London, pages 85-116. find
  5. Boguraev, Branimir and James Pustejovsky. 1996. Issues in text-based lexicon acquisition. In Branimir Boguraev and James Pustejovsky, editors, Corpus Processing for Lexical Acquisition. MIT Press, pages 3-20. find
  6. Brent, Michael. 1993. From grammar to lexicon: Unsupervised learning of lexical syntax. Computational Linguistics, 19(2):243-262. find
  7. Briscoe, Ted and John Carroll. 1997. Automatic extraction of subcategorization from corpora. In Proceedings of the Fifth Applied Natural Language Processing Conference, pages 356-363.
  8. Brousseau, Anne-Marie and Elizabeth Ritter. 1991. A non-unified analysis of agentive verbs. In West Coast Conference on Formal Linguistics, number 20, pages 53-64. find
  9. Burzio, Luigi. 1986. Italian Syntax: A Government-Binding Approach. Reidel: Dordrecht. find
  10. Carletta, Jean. 1996. Assessing agreement on classification tasks: the Kappa statistics. Computational Linguistics, 22(2):249-254. find
  11. Collins, Michael John. 1997. Three generative, lexicalised models for statistical parsing. In Proceedings of the 35th Annual Meeting of the ACL, pages 16-23, Madrid, Spain.
  12. Cruse, D. A. 1972. A note on English causatives. Linguistic Inquiry, 3(4):520-528. find
  13. Dang, Hoa Trang, Karin Kipper, Martha Palmer, and Joseph Rosenzweig. 1998. Investigating regular sense extensions based on intersective Levin classes. In Proceedings of the 36th Annual Meeting of the ACL and the 17th International Conference on Computational Linguistics (COLING-ACL "98), pages 293-2… find
  14. Dixon, Robert M. W. 1994. Ergativity. Cambridge University Press, Cambridge. find
  15. Dorr, Bonnie. 1997. Large-scale dictionary construction for foreign language tutoring and interlingual machine translation. Machine Translation, 12(4):1-55. find
  16. Dorr, Bonnie, Joe Garman, and Amy Weinberg. 1995. From syntactic encodings to thematic roles: Building lexical entries for interlingual MT. Journal of Machine Translation, 9(3):71-100. find
  17. Dorr, Bonnie and Doug Jones. 1996. Role of word sense disambiguation in lexical acquisition: Predicting semantics from syntactic cues. In Proceedings of the 16th International Conference on Computational Linguistics, pages 322-327, Copenhagen. find
  18. Dowty, David. 1991. Thematic proto-roles and argument selection. Language, 67(3):547-619. find
  19. Greenberg, Joseph H. 1966. Language Universals. Mouton, The Hague, Paris. find
  20. Gruber, Jeffrey. 1965. Studies in Lexical Relation. MIT Press, Cambridge, MA. find
  21. Hale, Ken and Jay Keyser. 1993. On argument structure and the lexical representation of syntactic relations. In K. Hale and J. Keyser, editors, The View from Building 20. MIT Press, pages 53-110. find
  22. Jakobson, Roman. 1971. Signe Z4ro. In Selected Writings, volume 2, 2d ed. Mouton, The Hague, pages 211-219. find
  23. Kariaeva, Natalia. 1999. Discriminating between unaccusative and object-drop verbs: Animacy factor. Ms., Rutgers University. New Brunswick, NJ. find
  24. Klavans, Judith and Martin Chodorow. 1992. Degrees of stativity: The lexical representation of verb aspect. In Proceedings of the Fourteenth International Conference on Computational Linguistics (COLING "92), pages 1126-1131, Nantes, France. find
  25. Klavans, Judith and Min-Yen Kan. 1998. Role of verbs in document analysis. In Proceedings of the 36th Annual Meeting of the ACL and the 17th International Conference on Computational Linguistics (COLING-ACL '98), pages 680-686, Montreal. Universit4 de Montreal. find
  26. Lapata, Maria. 1999. Acquiring lexical generalizations from corpora: A case study for diathesis alternations. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL'99), pages 397-404, College Park, MD. find
  27. Lapata, Maria and Chris Brew. 1999. Using subcategorization to resolve verb class ambiguity. In Proceedings of Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, pages 266-274, College Park, MD. find
  28. Levin, Beth. 1985. Introduction. In Beth Levin, editor, Lexical Semantics in Review, number 1 in Lexicon Project Working Papers. Centre for Cognitive Science, MIT, Cambridge, MA, pages 1-62. find
  29. Levin, Beth. 1993. English Verb Classes and Alternations. University of Chicago Press, Chicago, IL. find
  30. Levin, Beth and Malka Rappaport Hovav. 1995. Unaccusativity. MIT Press, Cambridge, MA. find
  31. Manning, Christopher D. 1993. Automatic acquisition of a large subcategorization dictionary from corpora. In Proceedings of the 31st Annual Meeting of the Association for Computational Linguistics, pages 235-242. find
  32. McCarthy, Diana. 2000. Using semantic preferences to identify verbal participation in role switching alternations. In Proceedings of ANLP-NAACL 2000, pages 256-263, Seattle, WA. find
  33. McCarthy, Diana and Anna Korhonen. 1998. Detecting verbal participation in diathesis alternations. In Proceedings of the 36th Annual Meeting of the ACL and the 17th International Conference on Computational Linguistics (COLING-ACL "98), pages 1493-1495, Montreal, Universit4 de Montreal. find
  34. Merlo, Paola and Suzanne Stevenson. 1998. What grammars tell us about corpora: the case of reduced relative clauses. In Proceedings of the Sixth Workshop on Very Large Corpora, pages 134-142, Montreal. find
  35. Merlo, Paola and Suzanne Stevenson. 2000a. Establishing the upper-bound and inter-judge agreement in a verb classification task. In Second International Conference on Language Resources and Evaluation (LREC-2000), volume 3, pages 1659-1664. find
  36. Merlo, Paola and Suzanne Stevenson. 2000b. Lexical syntax and parsing architecture. In Matthew Crocker, Martin Pickering, and Charles Clifton, editors, Architectures and Mechanisms for Language Processing. find
  37. Cambridge University Press, Cambridge, pages 161-188. find
  38. Moravcsik, Edith and Jessica Wirth. 1983. Markedness — an Overview. In Fred Eckman, Edith Moravcsik, and Jessica Wirth, editors, Markedness. Plenum Press, New York, NY, pages 1-13. find
  39. Oishi, Akira and Yuji Matsumoto. 1997. Detecting the organization of semantic subclasses of Japanese verbs. International Journal of Corpus Linguistics, 2(1):65-89. find
  40. Palmer, Martha. 2000. Consistent criteria for sense distinctions. Special Issue of Computers and the Humanities, SENSEVAL98: Evaluating Word Sense Disambiguation Systems, 34(1-2):217-222. find
  41. Perlmutter, David. 1978. Impersonal passives and the unaccusative hypothesis. In Proceedings of the Annual Meeting of the Berkeley Linguistics Society, volume 4, pages 157-189. find
  42. Pinker, Steven. 1989. Learnability and Cognition: the Acquisition of Argument Structure. MIT Press, Cambridge, MA. find
  43. Quinlan, J. Ross. 1992. C4.5: Programs for Machine Learning. Series in Machine Learning. Morgan Kaufmann, San Mateo, CA.
  44. Ratnaparkhi, Adwait. 1996. A maximum entropy parbof-speech tagger. In Proceedings of the Empirical Methods in Natural Language Processing Conference, pages 133-142, Philadelphia, PA. find
  45. Resnik, Philip. 1996. Selectional constraints: an information-theoretic model and its computational realization. Cognition, 61(1-2):127-160. find
  46. Riloff, Ellen and Mark Schmelzenbach. 1998. An empirical approach to conceptual case frame acquisition. In Proceedings of the Sixth Workshop on Very Large Corpora, pages 49-56. find
  47. Rosch, Eleanor. 1978. Principles of categorization. In Cognition and Categorization. Lawrence Erlbaum Assoc, Hillsdale, NJ. find
  48. Sanfilippo, Antonio and Victor Poznanski. 1992. The acquisition of lexical knowledge from combined machine-readable dictionary sources. In Proceedings of the Third Applied Natural Language Processing Conference, pages 80-87, Trento, Italy. find
  49. Schulte im Walde, Sabine. 2000. Clustering verbs semantically according to their alternation behaviour. In Proceedings of COLING 2000, pages 747-753, Saarbruecken, Germany. find
  50. Siegel, Eric 1998. Linguistic Indicators for Language Understanding: Using machine learning methods to combine corpus-based indicators for aspectual classification of clauses. find
  51. Ph.D. thesis, Dept. of Computer Science, Columbia University. find
  52. Siegel, Eric. 1999. Corpus-based linguistic indicators for aspectual classification. In Proceedings of ACL'99, pages 112-119, College Park, MD. University of Maryland. find
  53. Siegel, Sidney and John Castellan. 1988. find
  54. Nonparametric statistics for the Behavioral Sciences. McGraw-Hill, New York. find
  55. Silverstein, Michael. 1976. Hierarchy of features and ergativity. In Robert Dixon, editor, Grammatical Categories in Australian Languages. Australian Institute of Aboriginal Studies, Canberra, pages 112-171. find
  56. Srinivas, Bangalore and Aravind K. Joshi. 1999. Supertagging: An approach to almost parsing. Computational Linguistics, 25(2):237-265.
  57. Stede, Manfred. 1998. A generative perspective on verb alternations. Computational Linguistics, 24(3):401–430. find
  58. Stevenson, Suzanne and Paola Merlo. 1997a. Architecture and experience in sentence processing. In Proceedings of the 19th Annual Conference of the Cognitive Science Society, pages 715-720. find
  59. Stevenson, Suzanne and Paola Merlo. 1997b. Lexical structure and processing complexity. Language and Cognitive Processes, 12(1-2):349-399. find
  60. Stevenson, Suzanne, Paola Merlo, Natalia Kariaeva, and Kamin Whitehouse. 1999. Supervised learning of lexical semantic verb classes using frequency distributions. In Proceedings of SigLex99: Standardizing Lexical Resources (SigLex'99), pages 15-21, College Park, MD. find
  61. Trubetzkoy, Nicolaj S. 1939. Grundzage der Phonologie. Travaux du Cercle Linguistique de Prague, Prague. find
  62. Webster, Mort and Mitch Marcus. 1989. Automatic acquisition of the lexical semantics of verbs from sentence frames. In Proceedings of the 27th Annual Meeting of the Association for Computational Linguistics, pages 177-184, Vancouver, Canada. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/merlo-2001-automatic-verb-classification-based-statistical/