Learning Textual Entailment on a Distance Feature Space

  • Maria Teresa Pazienza
  • Marco Pennacchiotti
  • Fabio Massimo Zanzotto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3944)


Textual Entailment recognition is a very difficult task as it is one of the fundamental problems in any semantic theory of natural language. As in many other NLP tasks, Machine Learning may offer important tools to better understand the problem. In this paper, we will investigate the usefulness of Machine Learning algorithms to address an apparently simple and well defined classification problem: the recognition of Textual Entailment. Due to its specificity, we propose an original feature space, the distance feature space, where we model the distance between the elements of the candidate entailment pairs. The method has been tested on the data of the Recognizing Textual Entailment (RTE) Challenge.


Feature Space Semantic Similarity Graph Match Entailment Relation Common Subgraph 
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.
    Chierchia, G., McConnell-Ginet, S.: Meaning and Grammar: An introduction to Semantics. MIT Press, Cambridge (2001)Google Scholar
  2. 2.
    Dagan, I., Glickman, O.: Probabilistic textual entailment: Generic applied modeling of language variability. In: Proceedings of the Workshop on Learning Methods for Text Understanding and Mining, Grenoble, France (2004)Google Scholar
  3. 3.
    Basili, R., Moschitti, A., Pazienza, M.T.: Empirical investigation of fast text categorization over linguistic features. In: Proceedings of the 15th European Conference on Artificial Intelligence (ECAI 2002), Lyon, France (2002)Google Scholar
  4. 4.
    Joachims, T.: Learning to Classify Text using Support Vector Machines: Methods, Theory, and Algorithms. Kluwer Academic Publishers, Dordrecht (2002)CrossRefGoogle Scholar
  5. 5.
    Glickman, O., Dagan, I.: A probabilistic setting and lexical coocurrence model for textual entailment. In: Proceedings of the ACL-Workshop on Empirical Modeling of Semantic Equivalence and Entailment, Ann Arbor, Michigan (2005)Google Scholar
  6. 6.
    Corley, C., Mihalcea, R.: Measuring the semantic similarity of texts. In: Proceedings of the ACL-Workshop on Empirical Modeling of Semantic Equivalence and Entailment, Ann Arbor, Michigan (2005)Google Scholar
  7. 7.
    Dagan, I., Glickman, O., Magnini, B.: The pascal recognising textual entailment challenge. In: PASCAL Challenges Workshop, Southampton, UK (2005)Google Scholar
  8. 8.
    Miller, G.A.: WordNet: A lexical database for English. Communications of the ACM 38, 39–41 (1995)CrossRefGoogle Scholar
  9. 9.
    Resnik, P.: Using information content to evaluate semantic similarity. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, Montreal, Canada (1995)Google Scholar
  10. 10.
    Lin, D.: An information-theoretic definition of similarity. In: Proceedings of the 15th International Conference on Machine Learning, Madison, WI (1998)Google Scholar
  11. 11.
    Vanderwende, L., Coughlin, D., Dolan, B.: What syntax can contribute in entailment task. In: Proceedings of the 1st Pascal Challenge Workshop, Southampton, UK (2005)Google Scholar
  12. 12.
    Pazienza, M.T., Pennacchiotti, M., Zanzotto, F.M.: A linguistic inspection of textual entailment. In: Bandini, S., Manzoni, S. (eds.) AI*IA 2005. LNCS (LNAI), vol. 3673, pp. 315–326. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  13. 13.
    Raina, R., Haghighi, A., Cox, C., Finkel, J., Michels, J., Toutanova, K., MacCartney, B., de Marneffe, M.C., Manning, C.D., Ng, A.Y.: Robust textual inference using diverse knowledge sources. In: Proceedings of the 1st Pascal Challenge Workshop, Southampton, UK (2005)Google Scholar
  14. 14.
    Kouylekov, M., Magnini, B.: Tree edit distance for textual entailment. In: Proceedings of the International Conference Recent Advances of Natural Language Processing (RANLP 2005), Borovets, Bulgaria (2005)Google Scholar
  15. 15.
    Lin, D.: Dependency-based evaluation of minipar. In: Proceedings of theWorkshop on Evaluation of Parsing Systems at LREC 1998, Granada, Spain (1998)Google Scholar
  16. 16.
    Proceedings of the Seventh Message Understanding Conference (MUC-7), Virginia USA. Morgan Kaufmann, San Francisco (1998)Google Scholar
  17. 17.
    Joachims, T.: Making large-scale svm learning practical. In: Schlkopf, B., Burges, C., Smola, A. (eds.) Advances in Kernel Methods-Support Vector Learning. MIT Press, Cambridge (1999)Google Scholar
  18. 18.
    Collins, M., Duffy, N.: New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron. In: Proceedings of the ACL 2002, Philadelphia, PA (2002)Google Scholar
  19. 19.
    Moschitti, A.: A study on convolution kernels for shallow semantic parsing. In: Proceedings of the ACL 2004, Barcellona, Spain (2004)Google Scholar
  20. 20.
    Lin, D., Pantel, P.: DIRT, discovery of inference rules from text. In: Knowledge Discovery and Data Mining, pp. 323–328 (2001)Google Scholar
  21. 21.
    Harris, Z.: Distributional structure. In: Katz, J. (ed.) The Philosophy of Linguistics. Oxford University Press, New York (1985)Google Scholar
  22. 22.
    Glickman, O., Dagan, I.: Identifying lexical paraphrases from a single corpus: A case study for verbs. In: Proceedings of the International Conference Recent Advances of Natural Language Processing (RANLP 2003), Borovets, Bulgaria (2003)Google Scholar
  23. 23.
    Shearer, K., Bunke, H., Venkatesh, S., Kieronska, D.: Efficient graph mathicng for video indexing. Technical Report 1997, Department of Computer Science, Curtin University (1997)Google Scholar
  24. 24.
    Cho, C., Kim, J.: Recognizing 3-d objects by forward checking constrained tree search. PRL 13, 587–597 (1992)CrossRefGoogle Scholar
  25. 25.
    Borner, K., Pippig, E., Tammer, E.C., Coulon, C.H.: Structural similarity and adaptation. In: Smith, I., Faltings, B.V. (eds.) EWCBR 1996. LNCS, vol. 1168, pp. 58–75. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  26. 26.
    Sanders, K.E., Kettler, B.P., Hendler, J.: The case for graph-structured representations. In: Proceedings of the Second International Conference on Case-based Reasoning, pp. 245–254. Springer, Heidelberg (1997)Google Scholar
  27. 27.
    Bunke, H.: Graph matching: Theoretical foundations, algorithms, and applications. In: Vision Interface 2000, Montreal, pp. 82–88. Springer, Heidelberg (2000)Google Scholar
  28. 28.
    Bunke, H., Shearer, K.: A graph distance metric based on the maximal common subgraph. Pattern Recogn. Lett. 19, 255–259 (1998)CrossRefMATHGoogle Scholar
  29. 29.
    Basili, R., Zanzotto, F.M.: Parsing engineering and empirical robustness. Natural Language Engineering 8(2-3) (2002)Google Scholar
  30. 30.
    Pazienza, M.T., Pennacchiotti, M., Zanzotto, F.M.: Identifying relational concept lexicalisations by using general linguistic knowledge. In: ECAI, pp. 1071–1072 (2004)Google Scholar
  31. 31.
    Wu, D.: Stochastic inversion transduction grammars, with application to segmentation, bracketing, and alignment of parallel corpora. Computational Linguistics 23, 207–223 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Maria Teresa Pazienza
    • 1
  • Marco Pennacchiotti
    • 1
  • Fabio Massimo Zanzotto
    • 2
  1. 1.University of Roma Tor VergataRomaItaly
  2. 2.DISCoUniversity of Milano BicoccaMilanoItaly

Personalised recommendations