Skip to main content
SpringerLink
Log in

Textual Inference with Tree-Structured LSTM

  • Conference paper
  • First Online:
BNAIC 2016: Artificial Intelligence (BNAIC 2016)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 765))

Included in the following conference series:

Abstract

Textual Inference is a research trend in Natural Language Processing (NLP) that has recently received a lot of attention by the scientific community. Textual Entailment (TE) is a specific task in Textual Inference that aims at determining whether a hypothesis is entailed by a text. This paper employs the Child-Sum Tree-LSTM for solving the challenging problem of textual entailment. Our approach is simple and able to generalize well without excessive parameter optimization. Evaluation done on SNLI, SICK and other TE datasets shows the competitiveness of our approach.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://clic.cimec.unitn.it/composes/sick.html.

  2. 2.

    https://www.aclweb.org/aclwiki/index.php?title=Textual_Entailment_Resource_Pool.

  3. 3.

    http://nlp.stanford.edu/projects/snli.

  4. 4.

    Throughout the paper, we use the words ‘Premise’, ‘Text’ or ‘First text’ interchangeably to mean the same thing, except otherwise specified.

  5. 5.

    http://clic.cimec.unitn.it/composes/sick.html.

  6. 6.

    Specifically, the MIREL project: http://www.mirelproject.eu, which is drawn from our past project EUCases [6].

  7. 7.

    http://webdocs.cs.ualberta.ca/~miyoung2/COLIEE2016.

  8. 8.

    https://github.com/fchollet/keras.

References

  1. Androutsopoulos, I., Malakasiotis, P.: A survey of paraphrasing and textual entailment methods. J. Artif. Intell. Res. 38, 135–187 (2010)

    MATH  Google Scholar 

  2. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)

  3. Baudiš, P., Šedivỳ, J.: Sentence pair scoring: towards unified framework for text comprehension. arXiv preprint arXiv:1603.06127 (2016)

  4. Bentivogli, L., Clark, P., Dagan, I., Giampiccolo, D.: The seventh pascal recognizing textual entailment challenge. In: Proceedings of TAC 2011 (2011)

    Google Scholar 

  5. Boella, G., Di Caro, L., Humphreys, L., Robaldo, L., Rossi, R., van der Torre, L.: Eunomos, a legal document and knowledge management system for the web to provide relevant, reliable and up-to-date information on the law. In: Artificial Intelligence and Law (2016, to appear)

    Google Scholar 

  6. Boella, G., Di Caro, L., Graziadei, M., Cupi, L., Salaroglio, C.E., Humphreys, L., Konstantinov, H., Marko, K., Robaldo, L., Ruffini, C. and Simov, K., Violato, A., Stroetmann, V.: Linking legal open data: Breaking the accessibility and language barrier in european legislation and case law. In: Proceedings of the 15th International Conference on Artificial Intelligence and Law, ICAIL 2015. ACM, New York (2015)

    Google Scholar 

  7. Boella, G., Di Caro, L., Rispoli, D., Robaldo, L.: A system for classifying multi-label text into EuroVoc. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law, ICAIL 2013, pp. 239–240. ACM, New York (2013)

    Google Scholar 

  8. Boella, G., Di Caro, L., Robaldo, L.: Semantic relation extraction from legislative text using generalized syntactic dependencies and support vector machines. In: Morgenstern, L., Stefaneas, P., Lévy, F., Wyner, A., Paschke, A. (eds.) RuleML 2013. LNCS, vol. 8035, pp. 218–225. Springer, Heidelberg (2013). doi:10.1007/978-3-642-39617-5_20

    Chapter  Google Scholar 

  9. Bowman, S. R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. arXiv preprint arXiv:1508.05326 (2015)

  10. Chen, D., Manning, C.D.: A fast and accurate dependency parser using neural networks. In: EMNLP, pp. 740–750 (2014)

    Google Scholar 

  11. Chen, Q., Zhu, X., Ling, Z., Wei, S., Jiang, H.: Enhancing and combining sequential and tree lstm for natural language inference. arXiv preprint arXiv:1609.06038 (2016)

  12. Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. arXiv preprint arXiv:1601.06733 (2016)

  13. Dagan, I., Dolan, B., Magnini, B., Roth, D.: Recognizing textual entailment: rational, evaluation and approaches-erratum. Nat. Lang. Eng. 16(01), 105–105 (2010)

    Article  Google Scholar 

  14. Dagan, I., Glickman, O., Magnini, B.: The PASCAL recognising textual entailment challenge. In: Quiñonero-Candela, J., Dagan, I., Magnini, B., d’Alché-Buc, F. (eds.) MLCW 2005. LNCS, vol. 3944, pp. 177–190. Springer, Heidelberg (2006). doi:10.1007/11736790_9

    Chapter  Google Scholar 

  15. Feng, M., Xiang, B., Glass, M.R., Wang, L., Zhou, B.: Applying deep learning to answer selection: a study and an open task. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 813–820. IEEE (2015)

    Google Scholar 

  16. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  17. John, A.K., Di Caro, L., Boella, G.: Normas at semeval-2016 task 1: Semsim: a multi-feature approach to semantic text similarity. In: Proceedings of SemEval (2016)

    Google Scholar 

  18. Kim, M.Y., Xu, Y., Goebel, R.: A convolutional neural network in legal question answering (2015)

    Google Scholar 

  19. Kim, M.-Y., Xu, Y., Goebel, R.: Legal question answering using ranking SVM and syntactic/semantic similarity. In: Murata, T., Mineshima, K., Bekki, D. (eds.) JSAI-isAI 2014. LNCS, vol. 9067, pp. 244–258. Springer, Heidelberg (2015). doi:10.1007/978-3-662-48119-6_18

    Chapter  Google Scholar 

  20. Liu, P., Qiu, X., Huang, X.: Modelling interaction of sentence pair with coupled-LSTMs. arXiv preprint arXiv:1605.05573 (2016)

  21. Liu, Y., Sun, C., Lin, L., Wang, X.: Learning natural language inference using bidirectional LSTM model and inner-attention. arXiv preprint arXiv:1605.09090 (2016)

  22. Munkhdalai, T., Yu, H.: Neural semantic encoders. arXiv preprint arXiv:1607.04315 (2016)

  23. Parikh, A.P., Täckström, O., Das, D., Uszkoreit, J.: A decomposable attention model for natural language inference. arXiv preprint arXiv:1606.01933 (2016)

  24. Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, vol. 14, pp. 1532–1543 (2014)

    Google Scholar 

  25. Gaona, M.A.R., Gelbukh, A., Bandyopadhyay, S.: Recognizing textual entailment using a machine learning approach. In: Advances in Soft Computing, pp. 177–185 (2010)

    Google Scholar 

  26. Rocktäschel, T., Grefenstette, E., Hermann, K.M., Kočiskỳ, T., Blunsom, P.: Reasoning about entailment with neural attention. arXiv preprint arXiv:1509.06664 (2015)

  27. Sha, L., Li, S., Chang, B., Sui, Z., Jiang, T.: Recognizing textual entailment using probabilistic inference. In: EMNLP, pp. 1620–1625 (2015)

    Google Scholar 

  28. Socher, R., Huang, E., Pennin, J., Manning, C., Ng, A.: Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. In: Advances in Neural Information Processing Systems, pp. 801–809 (2011)

    Google Scholar 

  29. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  30. Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 (2015)

  31. Tan, M., Xiang, B., Zhou, B.: LSTM-based deep learning models for non-factoid answer selection. arXiv preprint arXiv:1511.04108 (2015)

  32. Wang, Z., Hamza, W., Florian, R.: Bilateral multi-perspective matching for natural language sentences. arXiv preprint arXiv:1702.03814 (2017)

  33. Weston, J., Chopra, S., Bordes, A.: Memory networks. arXiv preprint arXiv:1410.3916 (2014)

  34. Yin, W., Schütze, H., Xiang, B., Zhou, B.: Abcnn: attention-based convolutional neural network for modeling sentence pairs. arXiv preprint arXiv:1512.05193 (2015)

  35. Zanzotto, F.M., Pennacchiotti, M.: Expanding textual entailment corpora from wikipedia using co-training. In: Proceedings of the COLING-Workshop on The Peoples Web Meets NLP: Collaboratively Constructed Semantic Resources, vol. 128 (2010)

    Google Scholar 

Download references

Acknowledgments

Kolawole J. Adebayo has received funding from the Erasmus Mundus Joint International Doctoral (Ph.D.) programme in Law, Science and Technology. Luigi Di Caro and Guido Boella have received funding from the European Union’s H2020 research and innovation programme under the grant agreement No 690974 for the project “MIREL: MIning and REasoning with Legal texts”. Livio Robaldo has received funding from the European Union’s H2020 research and innovation programme under the grant agreement No 661007 for the project “ProLeMAS: PROcessing LEgal language in normative Multi-Agent Systems”.

Author information

Authors and Affiliations

  1. Dipartimento di Informatica, Universita Di Torino, Corso Svizzera 185, 10149, Torino, Italy

    Adebayo Kolawole John, Luigi Di Caro, Livio Robaldo & Guido Boella

Authors
  1. Adebayo Kolawole John
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luigi Di Caro
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Livio Robaldo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guido Boella
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Adebayo Kolawole John .

Editor information

Editors and Affiliations

  1. Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands

    Tibor Bosse

  2. Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands

    Bert Bredeweg

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Kolawole John, A., Di Caro, L., Robaldo, L., Boella, G. (2017). Textual Inference with Tree-Structured LSTM. In: Bosse, T., Bredeweg, B. (eds) BNAIC 2016: Artificial Intelligence. BNAIC 2016. Communications in Computer and Information Science, vol 765. Springer, Cham. https://doi.org/10.1007/978-3-319-67468-1_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-67468-1_2

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-67467-4

  • Online ISBN: 978-3-319-67468-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation