Advertisement

Syntactic Knowledge for Natural Language Inference in Portuguese

  • Erick Fonseca
  • Sandra M. Aluísio
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11122)

Abstract

Natural Language Inference (NLI) is the task of detecting relations such as entailment, contradiction and paraphrase in pairs of sentences. With the recent release of the ASSIN corpus, NLI in Portuguese is now getting more attention. However, published results on ASSIN have not explored syntactic structure, neither combined word embedding metrics with other types of features. In this work, we sought to remedy this gap, proposing a new model for NLI that achieves 0.72 F\(_1\) score on ASSIN, setting a new state of the art. Our feature analysis shows that word embeddings and syntactic knowledge are both important to achieve such results.

Keywords

Natural Language Inference Recognizing Textual Entailment Feature engineering Syntax 

Notes

Acknowledgments

This work was supported by FAPESP grant 2013/22973-0.

References

  1. 1.
    Agirre, E., et al.: SemEval-2015 Task 2: semantic textual similarity, English, Spanish and pilot on interpretability. In: Proceedings of the 9th International Workshop on Semantic Evaluation, SemEval 2015, pp. 252–263. Association for Computational Linguistics (2015)Google Scholar
  2. 2.
    Alves, A.O., Oliveira, H.G., Rodrigues, R.: ASAPP e Reciclagem no ASSIN: Alinhamento Semântico Automático de Palavras aplicado ao Português. Linguamática 8(2), 43–58 (2016)Google Scholar
  3. 3.
    Barbosa, L., Cavalin, P., Martins, B., Guimarães, V., Kormaksson, M.: Blue Man Group no ASSIN: Usando Representações Distribuídas para Similaridade Semântica e Inferência Textual. Linguamática 8(2), 15–22 (2016)Google Scholar
  4. 4.
    Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 632–642. The Association for Computational Linguistics (2015)Google Scholar
  5. 5.
    Chen, Q., Zhu, X., Ling, Z.H., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for natural language inference. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Long Papers, vol. 1, pp. 1657–1668. Association for Computational Linguistics (2017)Google Scholar
  6. 6.
    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).  https://doi.org/10.1007/11736790_9CrossRefGoogle Scholar
  7. 7.
    Dagan, I., Roth, D., Sammons, M., Zanzotto, F.M.: Recognizing Textual Entailment: Models and Applications. Synthesis Lectures on Human Language Technologies. Morgan & Claypool, San Rafael (2013)Google Scholar
  8. 8.
    Feitosa, D.B., Pinheiro, V.C.: Análise de medidas de similaridade semântica na tarefa de reconhecimento de implicação textual. In: Proceedings of Symposium in Information and Human Language Technology (2017)Google Scholar
  9. 9.
    Fialho, P., Marques, R., Martins, B., Coheur, L., Quaresma, P.: INESC-ID no ASSIN: measuring semantic similarity and recognizing textual entailment. Linguamática 8(2), 33–42 (2016)Google Scholar
  10. 10.
    Fonseca, E.R., dos Santos, L.B., Criscuolo, M., Aluísio, S.M.: Visão Geral da Avaliação de Similaridade Semântica e Inferência Textual. Linguamática 8(2), 3–13 (2016)Google Scholar
  11. 11.
    Hartmann, N.S.: Solo queue no ASSIN: mix of a traditional and an emerging approaches. Linguamática 8(2), 59–64 (2016)Google Scholar
  12. 12.
    Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S.J., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: Association for Computational Linguistics (ACL) System Demonstrations, pp. 55–60 (2014)Google Scholar
  13. 13.
    Marelli, M., Menini, S., Baroni, M., Bentivogli, L., Bernardi, R., Zamparelli, R.: A SICK cure for the evaluation of compositional distributional semantic models. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation, pp. 216–223. European Language Resources Association (ELRA) (2014)Google Scholar
  14. 14.
    de Paiva, V., Rademaker, A., de Melo, G.: OpenWordNet-PT: an open Brazilian WordNet for reasoning. In: Proceedings of the 24th International Conference on Computational Linguistics, COLING 2012, pp. 353–360 (2012)Google Scholar
  15. 15.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  16. 16.
    Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing, EMNLP, pp. 1532–1543 (2014). http://www.aclweb.org/anthology/D14-1162
  17. 17.
    Rocha, G., Cardoso, L.H.: Recognizing textual entailment: challenges in the Portuguese language. Information 9(4), 76 (2018)CrossRefGoogle Scholar
  18. 18.
    Shen, T., Zhou, T., Long, G., Jiang, J., Pan, S., Zhang, C.: DiSAN: directional self-attention network for RNN/CNN-free language understanding. ArXiv e-prints (2017)Google Scholar
  19. 19.
    Zanoli, R., Colombo, S.: A transformation-driven approach for recognizing textual entailment. Nat. Lang. Eng. 23(4), 507–534 (2016)CrossRefGoogle Scholar
  20. 20.
    Zhang, K., Shasha, D.: Simple fast algorithms for the editing distance between trees and related problems. SIAM J. Comput. 18, 1245–1262 (1989)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Institute of Mathematics and Computer ScienceUniversity of São PauloSão CarlosBrazil

Personalised recommendations