Advertisement

Abstract

We use logical inference techniques for recognising textual entailment, with theorem proving operating on deep semantic interpretations as the backbone of our system. However, the performance of theorem proving on its own turns out to be highly dependent on a wide range of background knowledge, which is not necessarily included in publically available knowledge sources. Therefore, we achieve robustness via two extensions. Firstly, we incorporate model building, a technique borrowed from automated reasoning, and show that it is a useful robust method to approximate entailment. Secondly, we use machine learning to combine these deep semantic analysis techniques with simple shallow word overlap. The resulting hybrid model achieves high accuracy on the RTE testset, given the state of the art. Our results also show that the various techniques that we employ perform very differently on some of the subsets of the RTE corpus and as a result, it is useful to use the nature of the dataset as a feature.

Keywords

Domain Size Theorem Prover Question Answering Word Sense Disambiguation Model Builder 
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, pp. 61–68 (2005)Google Scholar
  2. Blackburn, P., Bos, J.: Representation and Inference for Natural Language. A First Course in Computational Semantics. In: CSLI (2005)Google Scholar
  3. Bayer, S., Burger, J., Ferro, L., Henderson, J., Yeh, A.: Mitre’s submission to the eu pascal rte challenge. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment, pp. 41–44 (2005)Google Scholar
  4. Blackburn, P., Bos, J., Kohlhase, M., de Nivelle, H.: Inference and Computational Semantics. In: Bunt, H., Muskens, R., Thijsse, E. (eds.) Computing Meaning, vol. 2, pp. 11–28. Kluwer, Dordrecht (2001)CrossRefGoogle Scholar
  5. Bos, J., Clark, S., Steedman, M., Curran, J., Hockenmaier, J.: Widecoverage semantic representations from a ccg parser. In: Proc of the 20th International Conference on Computational Linguistics, Geneva, Switzerland (2004)Google Scholar
  6. Barzilay, R., Lee, L.: Learning to paraphrase: An unsupervised approach using multiple sequence alignment. In: NAACL-HLT 2003 (2003)Google Scholar
  7. Bos, J.: Implementing the Binding and Accommodation Theory for Anaphora Resolution and Presupposition Projection. Computational Linguistics (2003)Google Scholar
  8. Bos, J.: Towards wide-coverage semantic interpretation. In: Proceedings of Sixth International Workshop on Computational Semantics IWCS-6, pp. 42–53 (2005)Google Scholar
  9. Clark, S., Curran, J.R.: Parsing the WSJ using CCG and Log-Linear Models. In: Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL 2004), Barcelona, Spain (2004)Google Scholar
  10. Cooper, R., Crouch, R., Van Eijck, J., Fox, C., Van Genabith, J., Jaspars, J., Kamp, H., Pinkal, M., Milward, D., Poesio, M., Pulman, S.: Using the framework. Fracas: A framework for computationla semantics. Technical report, Fracas Deliverable D16 (1996)Google Scholar
  11. Claessen, K., Sörensson, N.: New techniques that improve mace-style model finding. In: Model Computationa - Principles, Algorithms, Applications (Cade-19 Workshop), Miami, Florida (2003)Google Scholar
  12. Dagan, I., Glickman, O., Magnini, B.: The pascal recognizing textual entailment challenge. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment, pp. 1–8 (2005)Google Scholar
  13. Fellbaum, C. (ed.): WordNet: An Electronic Lexical Database. MIT Press, Cambridge (1998)MATHGoogle Scholar
  14. Fowler, A., Hauser, B., Hodges, D., Niles, I., Novischi, A., Stephan, J.: Applying cogex to recognize textual entailment. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment, pp. 69–72 (2005)Google Scholar
  15. Herrera, J., Penas, A., Verdejo, F.: Textual entailment recognition based on dependency analysis and wordnet. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (2005)Google Scholar
  16. Jijkoun, V., de Rijke, M.: Recognising textual entailment using lexical similarity. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (2005)Google Scholar
  17. Kamp, H., Reyle, U.: From Discourse to Logic. Introduction to Modeltheoretic Semantics of Natural Language. In: Formal Logic and Discourse Representation Theory. Kluwer, Dordrecht (1993)Google Scholar
  18. Monz, C., de Rijke, M.: Light-weight entailment checking for computational semantics. In: Proc. of the 3rd Workshop on Inference in Computational Semantics (2003)Google Scholar
  19. Manning, C., Schuetze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)Google Scholar
  20. Newman, E., Stokes, N., Dunnion, J., Carthy, J.: Ucd iirg approach to the textual entailment challenge. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (2005)Google Scholar
  21. Perez, D., Alfonseca, E.: Application of the bleu algorithm for recognising textual entailments. In: Proceedings of the PASCAL Challenges Workshop on Recognising Textual Entailment (2005)Google Scholar
  22. Raina, R., Ng, A.Y., Manning, C.: Robust textual inference via learning and abductive reasoning. In: Proc. of AAAI 2005 (2005)Google Scholar
  23. Riazanov, A., Voronkov, A.: The design and implementation of Vampire. AI Communications 15(2-3) (2002)Google Scholar
  24. Saggion, H., Gaizauskas, R., Hepple, M., Roberts, I., Greenwood, M.: Exploring the performance of boolean retrieval strategies for open domain question answering. In: Proc. of the Information Retrieval for Question Answering (IR4QA) Workshop at SIGIR 2004 (2004)Google Scholar
  25. Steedman, M.: The Syntactic Process. MIT Press, Cambridge (2001)Google Scholar
  26. Van der Sandt, R.A.: Presupposition Projection as Anaphora Resolution. Journal of Semantics 9, 333–377 (1992)CrossRefGoogle Scholar
  27. Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Diego (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Johan Bos
    • 1
  • Katja Markert
    • 2
  1. 1.School of InformaticsUniversity of EdinburghUK
  2. 2.School of ComputingUniversity of LeedsUK

Personalised recommendations