Advertisement

Combining Transformation and Classification for Recognizing Textual Entailment

  • Han Ren
  • Jing WanEmail author
  • Xiaomei Chen
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 986)

Abstract

This paper introduces an approach combining transformation and classification methods for recognizing textual entailment. In transformation model, directional and undirected inference relations are recognized, and text fragments having such relations in text are replaced by the counterparts in hypothesis. In classification model, a hybrid kernel-based approach is introduced, and three kinds of features are employed for classifying entailment. Experimental results show that the combination approach achieves a better performance in comparison with the single classification system.

Notes

Acknowledgements

This work is supported by Natural Science Foundation of Hainan (618MS086), Special innovation project of Guangdong Education Department (2017KTSCX064), Natural Science Foundation of China (61702121) and Bidding Project of GDUFS Laboratory of Language Engineering and Computing (LEC2016ZBKT001, LEC2016ZBKT002).

References

  1. 1.
    Dagan, I., Dolan, B.: Recognizing textual entailment: rational, evaluation and approaches. Nat. Lang. Eng. 15(4), i–xvii (2009)CrossRefGoogle Scholar
  2. 2.
    Bar-Haim, R., Berant, J., Dagan, I., Greental, I., Mirkin, S., Shnarch, E., et al.: Efficient semantic deduction and approximate matching over compact parse forests. In: Proceedings of the Fourth PASCAL Challenges Workshop on Recognizing Textual Entailment, Gaithersburg, Maryland, USA (2008)Google Scholar
  3. 3.
    Watanabe, Y., Miyao, Y., Mizuno, J., Shibata, T., Kanayama, H., Lee, C.-W., et al.: Overview of the recognizing inference in text (RITE-2) at the NTCIR-10 workshop. In: Proceedings of the 10th NTCIR Workshop, Tokyo, Japan (2013)Google Scholar
  4. 4.
    Agichtein, E., Askew, W., Liu, Y.: Combining lexical, syntactic, and semantic evidence for textual entailment classification. In: Proceedings of the Fourth PASCAL Challenges Workshop on Recognizing Textual Entailment, Gaithersburg, Maryland, USA (2008)Google Scholar
  5. 5.
    Galanis, D., Malakasiotis, P.: AUEB at TAC 2008. In: Proceedings of the Fourth PASCAL Challenges Workshop on Recognizing Textual Entailment, Gaithersburg, Maryland, USA (2008)Google Scholar
  6. 6.
    Ren, H., Ji, D., Wan, J.: WHU at TAC 2009: a tri-categorization approach to textual entailment recognition. In: Proceedings of the Fifth PASCAL Challenges Workshop on Recognizing Textual Entailment, Gaithersburg, Maryland, USA (2009)Google Scholar
  7. 7.
    Wang, R., Neumann, G.: A divide-and-conquer strategy for recognizing textual entailment. In: Proceedings of the Fourth PASCAL Challenges Workshop on Recognizing Textual Entailment, Gaithersburg, Maryland, USA (2008)Google Scholar
  8. 8.
    Pham, Q.N.M., Nguyen, L.M., Shimazu, A.: A machine learning based textual entailment recognition system of JAIST team for NTCIR9 RITE. In: Proceedings of the 9th NTCIR Workshop, Tokyo, Japan (2011)Google Scholar
  9. 9.
    Ren, H., Ji, D., Wan, J.: The WHUTE system in NTCIR-9 RITE task. In: Proceedings of the 8th NTCIR Workshop Meeting, Tokyo, Japan (2011)Google Scholar
  10. 10.
    Akiba, Y., Taira, H., Fujita, S.: NTTCS textual entailment recognition system for NTCIR-9 RITE. In: Proceedings of the 9th NTCIR Workshop, Tokyo, Japan (2011)Google Scholar
  11. 11.
    Huang, H.-H., Chang, K.-C., Haver II, J.M., Chen, H.-H.: NTU textual entailment system for NTCIR 9 RITE task. In: Proceedings of the 9th NTCIR Workshop, Tokyo, Japan (2011)Google Scholar
  12. 12.
    Pakray, P., Neogi, S., Bandyopadhyay, S., Gelbukh, A.: A textual entailment system using web based machine translation system. In: Proceedings of the 9th NTCIR Workshop, Tokyo, Japan (2011)Google Scholar
  13. 13.
    Winkler, W.E.: String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. In: Proceedings of the Section on Survey Research Methods, pp. 354–359, American Statistical Association (1990)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Laboratory of Language Engineering and ComputingGuangdong University of Foreign StudiesGuangzhouChina
  2. 2.Center for Lexicographical StudiesGuangdong University of Foreign StudiesGuangzhouChina
  3. 3.School of Information Science and TechnologyGuangdong University of Foreign StudiesGuangzhouChina

Personalised recommendations