Advertisement

Applying COGEX to Recognize Textual Entailment

  • Daniel Hodges
  • Christine Clark
  • Abraham Fowler
  • Dan Moldovan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3944)

Abstract

This paper describes the system that LCC has devised to perform textual entailment recognition for the PASCAL RTE Challenge. Our system transforms each text-hypothesis pair into a two-layered logic form representation that expresses the lexical, syntactic, and semantic attributes of the text and hypothesis. A large set of natural language axioms are constructed for each text-hypothesis pair that help connect concepts in the hypothesis with concepts in the text. Our natural language logic prover is then used to prove entailment through abductive reasoning. The system’s performance in the challenge resulted in an accuracy of 55%.

Keywords

Noun Phrase Semantic Relation Word Sense Disambiguation Name Entity Abductive Reasoning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Akhmatova, E.: Textual Entailment Resolution via Atomic Propositions. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (April 2005)Google Scholar
  2. Bobrow, D., Condoravdi, C., Crouch, R., Kaplan, R., Karttunen, L., King, T., de Paiva, V., Zaenen, A.: A Basic Logic for Textual Inference. In: Papers from the AAAI 2005 Workshop on Inference for Textual Question Answering, pp. 47–51. AAAI Press, Menlo Park (2005)Google Scholar
  3. de Salvo Braz, R., Girju, R., Punyakanok, V., Roth, D., Sammons, M.: An Inference Model for Semantic Entailment in Natural Language. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (April 2005)Google Scholar
  4. Clark, C., Hodges, D., Stephan, J., Moldovan, D.: Moving QA Towards Reading Comprehension Using Context and Default Reasoning. In: Papers from the AAAI 2005 Workshop on Inference for Textual Question Answering, pp. 6–12. AAAI Press, Menlo Park (2005)Google Scholar
  5. Collins, M.: Head-Driven Statistical Models for Natural Language Parsing. Computational Linguistics 29(4), 589–637 (2003)MathSciNetCrossRefMATHGoogle Scholar
  6. Dagan, I., Glickman, O., Magnini, B.: The PASCAL Recognising Textual Entailment Challenge. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (April 2005)Google Scholar
  7. Hobbs, J., Stickel, M., Martin, P.: Interpretation as abduction. Artificial Intelligence 63, 69–142 (1993)CrossRefGoogle Scholar
  8. Miller, G.: Wordnet: an online lexical database. International Journal of Lexicography 3(4) (1990)Google Scholar
  9. Moldovan, D., Badulescu, A., Tatu, M., Antohe, D., Giru, R.C.: Models for the semantic classification of noun phrases. In: Proceedings of HLT/NAACL, Computational Lexical Semantics workshop, Boston, Massachusetts (2004)Google Scholar
  10. Moldovan, D., Clark, C., Harabagiu, S., Maiorano, S.: Cogex: A Logic Prover for Question Answering. In: Proceedings of the Human Language Technology and North American Chapter of the Association for Computational Linguistics Conference (HLT 2003), Edmonton, Alberta, Canada, pp. 87–93 (2003)Google Scholar
  11. Moldovan, D., Novischi, A.: Lexical Chains for Question Answering. In: Proceedings of 19th International Conference on Computational Linguistics (COLING-2002), Taipei, Taiwan, pp. 674–680 (2002)Google Scholar
  12. Moldovan, D., Rus, V.: Logic Form Transformation of WordNet and its Applicability to QuestionAnswering. In: Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL 2001), Toulouse, France, pp. 394–401 (2001)Google Scholar
  13. Raina, R., Haghighi, A., Cox, C., Finkel, J., Michels, J., Toutanova, K., MacCartney, B., Marneffe, B., Manning, C.D., Ng, A.Y.: Robust Textual Inference using Diverse Knowledge Sources. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (April 2005)Google Scholar
  14. Russell, S., Norvig, P.: Artificial Inteligence – A Modern Approach. Prentice Hall, Englewood Cliffs (2003)MATHGoogle Scholar
  15. Tari, L., Baral, C.: Using AnsProlog with Link Grammar and WordNet for QA with deep reasoning. In: Papers from the AAAI 2005 Workshop on Inference for Textual Question Answering, pp. 13–21. AAAI Press, Menlo Park (2005)Google Scholar
  16. Wos, L.: Automated Reasoning. Basic Research Problems, vol. 33. Prentice Hall, Englewood Cliffs (1998)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Daniel Hodges
    • 1
  • Christine Clark
    • 1
  • Abraham Fowler
    • 1
  • Dan Moldovan
    • 1
  1. 1.Language Computer CorporationRichardsonUSA

Personalised recommendations