An Inference Model for Semantic Entailment in Natural Language

  • Rodrigo de Salvo Braz
  • Roxana Girju
  • Vasin Punyakanok
  • Dan Roth
  • Mark Sammons
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3944)


Semantic entailment is the problem of determining if the meaning of a given sentence entails that of another. We present a principled approach to semantic entailment that builds on inducing re-representations of text snippets into a hierarchical knowledge representation along with an optimization-based inferential mechanism that makes use of it to prove semantic entailment. This paper provides details and analysis of the knowledge representation and knowledge resources issues encountered. We analyze our system’s behavior on the PASCAL text collection and the PARC collection of question-answer pairs. This is used to motivate and explain some of the design decisions in our hierarchical knowledge representation, that is centered around a predicate-argument type abstract representation of text.


Weighting Scheme Inference Model Target Sentence Verb Processing Question Answering 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Dagan, I., Glickman, O.: Probabilistic textual entailment: Generic applied modeling of language variability. In: Learning Methods for Text Understanding and Mining, Grenoble, France (2004)Google Scholar
  2. 2.
    Schubert, L.K.: From english to logic: Contex-free computation of ‘conventional’ logical translations. In: Grosz, B.J., Sparck Jones, K., Webber, B.L. (eds.) Natural Language Processing. Kaufmann, Los Altos (1986)Google Scholar
  3. 3.
    Moore, R.C.: Problems in logical form. In: Grosz, B.J., Sparck Jones, K., Webber, B.L. (eds.) Natural Language Processing. Kaufmann, Los Altos (1986)Google Scholar
  4. 4.
    Hobbs, J.R., Stickel, M., Martin, P., Edwards, D.: Interpretation as abduction. In: Proc. of the 26th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 95–103 (1988)Google Scholar
  5. 5.
    Cumby, C.M., Roth, D.: Learning with feature description logics. In: Matwin, S., Sammut, C. (eds.) ILP 2002. LNCS (LNAI), vol. 2583, pp. 32–47. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  6. 6.
    Lloyd, J.W.: Foundations of Logic Progamming. Springer, Heidelberg (1987)CrossRefGoogle Scholar
  7. 7.
    Kingsbury, P., Palmer, M., Marcus, M.: Adding semantic annotation to the Penn. treebank. In: Proc. of the 2002 Human Language Technology conference (HLT), San Diego, CA (2002)Google Scholar
  8. 8.
    Baader, F., Calvanese, D., McGuinness, D., Nardi, D., Patel-Schneider, P.: Description Logic Handbook. Cambridge (2003)Google Scholar
  9. 9.
    Even-Zohar, Y., Roth, D.: A sequential model for multi class classification. In: Proc. of the 2001 Conference on Empirical Methods for Natural Language Processing (EMNLP), pp. 10–19 (2001)Google Scholar
  10. 10.
    Collins, M.: Head-driven Statistical Models for Natural Language Parsing. PhD thesis, Computer Science Department, University of Pennsylvenia, Philadelphia (1999)Google Scholar
  11. 11.
    Punyakanok, V., Roth, D., Yih, W., Zimak, D.: Semantic role labeling via integer linear programming inference. In: Proc. of the 20th International Conference on Computational Linguistics (COLING), Geneva, Switzerland (2004)Google Scholar
  12. 12.
    Punyakanok, V., Roth, D., Yih, W.: The necessity of syntactic parsing for semantic role labeling. In: Proc. of the 19th International Joint Conference on Artificial Intelligence, IJCAI (2005)Google Scholar
  13. 13.
    Li, X., Morie, P., Roth, D.: Identification and tracing of ambiguous names: Discriminative and generative approaches. In: Proc. of the 19th National Conference on Artificial Intelligence, AAAI (2004)Google Scholar
  14. 14.
    Fellbaum, C.: WordNet: An Electronic Lexical Database. MIT Press, Cambridge (1998)MATHGoogle Scholar
  15. 15.
    Lin, D., Pantel, P.: DIRT: discovery of inference rules from text. In: Proc. of ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2001, pp. 323–328 (2001)Google Scholar
  16. 16.
    Roth, D., Yih, W.: A linear programming formulation for global inference in natural language tasks. In: Proceedings of CoNLL-2004, pp. 1–8 (2004)Google Scholar
  17. 17.
    Roth, D., Yih, W.: Integer linear programming inference for conditional random fields. In: Proceedings of the International Conference on Machine Learning, ICML (2005)Google Scholar
  18. 18.
    Durme, B.V., Huang, Y., Kupsc, A., Nyberg, E.: Towards light semantic processing for question answering. In: HLT Workshop on Text Meaning (2003)Google Scholar
  19. 19.
    Moldovan, D., Clark, C., Harabagiu, S., Maiorano, S.: Cogex: A logic prover for question answering. In: Proc. of HLT-NAACL 2003 (2003)Google Scholar
  20. 20.
    Thompson, C., Mooney, R., Tang, L.: Learning to parse NL database queries into logical form. In: Workshop on Automata Induction, Grammatical Inference and Language Acquisition (1997)Google Scholar
  21. 21.
    Glickman, O., Dagan, I., Koppel, M.: A probabilistic classification approach for lexical textual entailment. In: Proc. of AAAI 2005 (2005)Google Scholar
  22. 22.
    Raina, R., Ng, A., Manning, C.: Robust textual inference via learning and abductive reasoning. In: Proc. of AAAI 2005 (2005)Google Scholar
  23. 23.
    Punyakanok, V., Roth, D., Yih, W.: Natural language inference via dependency tree mapping: An application to question answering. Technical Report No. UIUCDCS-R-2004-2443), UIUC Computer Science Department (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rodrigo de Salvo Braz
    • 1
  • Roxana Girju
    • 1
  • Vasin Punyakanok
    • 1
  • Dan Roth
    • 1
  • Mark Sammons
    • 1
  1. 1.Department of Computer ScienceUniversity of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations