Elamur Research⌕
☰
home / papers / 2000 / Learning Methods to Combine Linguistic Indicators:Improving Aspectual Classification and Revealing Linguistic Insights

Learning Methods to Combine Linguistic Indicators:Improving Aspectual Classification and Revealing Linguistic Insights

Paper · 2000 · Eric V. Siegel and Kathleen R. McKeown

Summary

Siegel and McKeown address automatic aspectual classification: assigning verbs and clauses to basic temporal categories. The key splits are states versus events, and culminated versus nonculminated events. Systems need these categories to read temporal modifiers and to order events in discourse. This capability matters for interpreting and generating language, producing summaries, retrieving information and translating text between languages.

Earlier work used "linguistic indicators": corpus counts of how often a verb appears with markers such as the progressive or particular temporal adverbials. On its own, each indicator gives only a partial and unreliable signal. The authors therefore combine 14 such indicators using three supervised learners: decision trees, genetic programming and logistic regression. They train separately for stativity and for completedness, and evaluate on an unrestricted set of verbs from two corpora, medical discharge summaries and novels.

The combined models outperform a baseline on both distinctions with little overfitting. Each task ends up weighting the indicators differently, and inspecting the learned models yields linguistic insights about aspect. An unsupervised co-occurrence clustering method is also tested and turns out to separate verbs by stativity. Together, the work offers a scalable, extensible approach to automatic aspectual classification.

Key points

  • The framework follows Moens and Steedman (1988). It uses three aspectual distinctions (stativity, completedness/telicity, atomicity), which yield five categories: state, culmination, culminated process, process and point.
  • The method combines 14 corpus-based linguistic indicators. Examples are co-occurrence with the progressive, the perfect, and duration phrases like "in an hour".
  • Three supervised learners are compared: decision trees, genetic programming and logistic regression. All three beat the baseline for both stativity and completedness.
  • Evaluation covers two corpora, medical discharge summaries and a collection of novels, using unrestricted verb sets.
  • An unsupervised meaning-based verb clustering approach is also evaluated and is found to reflect the stativity distinction. The exact accuracy figures were not in the excerpt provided.

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

🎓Columbia UniversityNew York · United States241 works · 54,053 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 Eric V. Siegel and Kathleen R. McKeown. 2000. Learning Methods to Combine Linguistic Indicators:Improving Aspectual Classification and Revealing Linguistic Insights. Computational Linguistics.

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

@article{siegel2000learning,
  title = {{Learning Methods to Combine Linguistic Indicators:Improving Aspectual Classification and Revealing Linguistic Insights}},
  author = {Eric V. Siegel and Kathleen R. McKeown},
  journal = {Computational Linguistics},
  year = {2000},
  doi = {10.1162/089120100750105957},
  url = {https://doi.org/10.1162/089120100750105957}
}

References

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

  1. Allen, Franklin and Risto Karjalainen. 1995. Using genetic algorithms to find technical trading rules. Technical Report, Rodney L. White Center For Financial Research. find
  2. Allen, James. 1995. Natural Language Understanding. Benjamin/Cummings, Redwood City, CA. find
  3. Baker, R. J. and J. A. Nelder. 1989. The GLIM System, Release 3: Generalized Linear Interactive Modeling. Numerical Algorithms Group, Oxford. find
  4. Black, Ezra. 1988. An experiment in computational discrimination of English word senses. IBM Journal of Research and Development, 2(32). find
  5. Breiman, Leo, Jerome H. Friedman, Richard A. Olshen, and Charles J. Stone. 1984. Classification and Regression Trees. Wadsworth, Belmont. find
  6. Brodley, Carla E. 1996. Applying classification algorithms in practice. In Statistics and Computing. find
  7. Cardie, Claire and Nicholas Howe. 1997. Improving minority class prediction using case-specific feature weights. In D. Fisher, editor, Proceedings of the Fourteenth International Conference on Machine Learning. Morgan Kaufmann. find
  8. Cardie, Claire and Raymond J. Mooney. 1999. Guest editors' introduction: Machine learning and natural language. Machine Learning, 1-3(34). find
  9. Chan, Philip K. and Sal J. Stolfo. 1993. Toward multistrategy parallel and distributed learning in sequence analysis. In Proceedings of the First International Conference on Intelligent Systems for Molecular Biology. find
  10. Church, Ken. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the 2nd Conference for Applied Natural Language Processing, pages 136-143.
  11. Cohen, William W. 1995. Fast effective rule induction. In Proceedings of the 12th International Conference on Machine Learning, pages 115-123. find
  12. Cramer, Nichael L. 1985. A representation for the adaptive generation of simple sequential programs. In J. Grefenstette, editor, Proceedings of the [First] International Conference on Genetic Algorithms. Lawrence Erlbaum. find
  13. Dorr, Bonnie J. 1992. A two-level knowledge representation for machine translation: lexical semantics and tense/aspect. In James Pustejovsky and Sabine Bergler, editors, Lexical Semantics and Knowledge Representation. Springer Verlag, Berlin. find
  14. Dowty, David R. 1979. Word Meaning and Montague Grammar. D. Reidel, Dordrecht. find
  15. Duda, Richard O. and Peter E. Hart. 1973. Pattern Class~cation and Scene Analysis. Wiley, New York. find
  16. Fayyad, Usama M. and Keki B. Irani. 1992. On the handling of continuous-valued attributes in decision tree generation. Machine Learning, 8. find
  17. Friedman, Jerome H. 1977. A recursive partitioning decision rule for non-parametric classification. IEEE Transactions on Computers. find
  18. Goldberg, David. 1989. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Publishing Company, Inc., Reading, MA. find
  19. Hatzivassiloglou, Vasileios. 1997. Automatic Acquisition of Lexical Semantic Knowledge from Large Corpora: The Identi~cation of Semantically Related Words, Markedness, Polarity, and Antonymy. Ph.D. thesis, Columbia University. find
  20. Hatzivassiloglou, Vasileios and Kathleen R. McKeown. 1993. Towards the automatic identification of adjectival scales: clustering adjectives according to meaning. In Proceedings of the 31st Annual Meeting, pages 172-182, Columbus, OH, June. Association for Computational Linguistics. find
  21. Hatzivassiloglou, Vasileios and Kathleen R. McKeown. 1995. A quantitative evaluation of linguistic tests for the automatic prediction of semantic markedness. In Proceedings of the 33rd Annual Meeting, pages 197-204, Boston, MA, June. Association for Computational Linguistics. find
  22. Hitzeman, Janet, Marc Moens, and Claire Grover. 1994. Algorithms for analysing the temporal structure of discourse. Technical Report, University of Edinburgh. find
  23. Holland, John. 1975. Adaptation in Natural and Art~cial Systems. The University of Michigan Press, Ann Arbor, MI. find
  24. Hwang, Chung Hee and Lenhart K. Schubert. 1991. Interpreting temporal adverbials. Technical Report, University of Rochester. find
  25. Klavans, Judith L. 1994. Linguistic tests over large corpora: aspectual classes in the lexicon. Technical Report, Columbia University Dept. of Computer Science. find
  26. Klavans, Judith L. and Martin Chodorow. 1992. Degrees of stativity: the lexical representation of verb aspect. In Proceedings of the 14th International Conference on Computation Linguistics. find
  27. Knight, K., I. Chander, M. Haines, V. Hatzivassiloglou, E. Hovy, M. Iida, S. K. Luk, R. Whitney, and K. Yamada. 1995. Filling knowledge gaps in a broad-coverage mt system. In Proceedings of the International Joint Conference on ArtiJicial Intelligence. find
  28. Koza, John R. 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA. find
  29. Litman, Diane J. 1994. Classifying cue phrases in text and speech using machine learning. In Proceedings of the Twelfth National Conference on Artificial Intelligence, Menlo Park, CA, July. AAAI Press. find
  30. Luk, Alpha K. 1995. Statistical sense disambiguation with relatively small corpora using dictionary definitions. In Proceedings of the 33rd Annual Meeting, Columbus, OH, June. Association for Computational Linguistics. find
  31. Magerman, David H. 1993. Parsing as statistical pattern recognition. Technical Report, IBM. find
  32. Masand, Brij. 1994. Optimizing confidence of text classification by evolution of symbolic expressions. In K. Kinnear, editor, Advances in Genetic Programming. MIT Press, Cambridge, MA. find
  33. McCord, Michael C. 1990. SLOT GRAMMAR: A system for simpler construction of practical natural language grammars. In R. Studer, editor, International Symposium on Natural Language and Logic. Springer Verlag. find
  34. Mitchell, Tom M. 1997. Machine Learning. The McGraw-Hill Companies, Inc., New York. find
  35. Moens, Marc and Mark Steedman. 1988. Temporal ontology and temporal reference. Computational Linguistics, 14(2). find
  36. Olsen, Mari B. and Philip Resnik. 1997. Implicit object constructions and the (in)transitivity continuum. In Proceedings of the 33rd Regional Meeting of the Chicago Linguistics Society, April. find
  37. Passonneau, Rebecca J. 1988. A computational model of the semantics of tense and aspect. Computational Linguistics, 14(2). find
  38. Pereira, Fernando, Naftali Tishby, and Lillian Lee. 1993. Distributional clustering of English words. In Proceedings of the 31st Annual Meeting, pages 183-190, Columbus, OH, June. Association for Computational Linguistics.
  39. Powers, David M. W. and Christopher C. R. Turk. 1989. Machine Learning of Natural Language. Springer-Verlag. find
  40. Pustejovsky, James. 1991. The syntax of event structure. Cognition, 41(103):47-92. find
  41. Pustejovsky, James. 1995. The Generative Lexicon. MIT Press, Cambridge, MA. find
  42. Quinlan, Jim R. 1986. Induction of decision trees. Machine Learning, 1(1):81-106. find
  43. Quinlan, Jim R. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo, CA.
  44. Resnik, Philip. 1993. Semantic classes and syntactic ambiguity. In Proceedings of the ARPA Workshop on Human Language Technology, March. find
  45. Resnik, Philip. 1996. Selectional constraints: An information-theoretic model and its computational realization. Cognition, (61). find
  46. Schfitze, Hinrich. 1992. Dimensions of meaning. In Proceedings of Supercomputing. find
  47. Schubert, Lenhart K. and Chung Hee Hwang. 1990. Picking reference events from tense trees: A formal, implementable theory of English tense-aspect semantics. Technical Report, University of Rochester. find
  48. Siegel, Eric V. 1994. Competitively evolving decision trees against fixed training cases for natural language processing. In K. Kinnear, editor, Advances in Genetic Programming. MIT Press, Cambridge, MA. find
  49. Siegel, Eric V. 1997. Learning methods for combining linguistic indicators to classify verbs. In Proceedings of the Second Conference on Empirical Methods in Natural Language Processing, Providence, RI, August. find
  50. Siegel, Eric V. 1998a. Disambiguating verbs with the WordNet category of the direct object. In Proceedings of the Usage of WordNet in Natural Language Processing Systems Workshop, Montreal, Canada. find
  51. Siegel, Eric V. 1998b. Linguistic Indicators for Language Understanding: Using Machine Learning Methods to Combine Corpus-based Indicators for Aspectual Classification of Clauses. Ph.D. thesis, Columbia University. find
  52. Siegel, Eric V. 1999. Corpus-based linguistic indicators for aspectual classification. In Proceedings of the 37th Annual Meeting. Association for Computational Linguistics. find
  53. Siegel, Eric V. and Kathleen R. McKeown. 1994. Emergent linguistic rules from inducing decision trees: disambiguating discourse clue words. In Proceedings of the Twelfth National Conference on Artificial Intelligence, Menlo Park, CA, July. AAAI Press. find
  54. Siegel, Eric V. and Kathleen R. McKeown. 1996. Gathering statistics to aspectually classify sentences with a genetic algorithm. In K. Oflazer and H. Somers, editors, Proceedings of the Second International Conference on New Methods in Language Processing, Ankara, Turkey, September, Bilkent Universit… find
  55. Sjantner, T. J. and D. E. Duffy. 1989. The Statistical Analysis of Discrete Data. Springer-Verlag, New York. find
  56. Stolfo, Salvatore, Andreas L. Prodromidis, Shelley Tselepis, Wenke Lee, and Wei Fan. 1997. JAM: Java agents for meta-learning over distributed databases. Technical Report, Columbia University. find
  57. Stys, Malgorzata E. 1991. Parallel science texts in English and Polish: Problems of language and communication. Technical Report, Warsaw University. Master's thesis. find
  58. Syswerda, Gibert. 1989. Uniform crossover in genetic algorithms. In J. D. Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms. Morgan Kaufmarm. find
  59. Tackett, Walter A. 1993. Genetic programming for feature discovery and image discrimination. In Proceedings of the Fifth International Conference on Genetic Algorithms, San Mateo, CA. Morgan Kaufmann. find
  60. Tackett, Walter A. and Aviram Carmi. 1994. The donut problem: Scalability, generalization and breeding policies in genetic programming. In K. Kinnear, editor, Advances in Genetic Programming. MIT Press, Cambridge, MA. find
  61. Vendler, Zeno. 1967. Verbs and times. In Linguistics in Philosophy. CorneU University Press, Ithaca, NY. find
  62. Wiebe, Janyce M., Thomas P. O'Hara, Thorsten Ohrstr6m-Sandgren, and Kenneth J. McKeever. 1997. An empirical approach to temporal reference resolution. In Proceedings of the Second Conference on Empirical Methods in Natural Language Processing, Providence, RI, August. find
  63. Wolpert, David H. 1992. Stacked generalization. Neural Networks, 5. find
  64. Yarowsky, David. 1994. Decision lists for lexical ambiguity resolution: Application to accent restoration in Spanish and French. In Proceedings of the 32nd Annual Meeting, San Francisco, CA, June. Morgan Kaufmann. Association for Computational Linguistics.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/siegel-2000-learning-methods-combine-linguistic-indicators/