Determining semantic textual similarity using natural deduction proofs

Hitomi Yanaka, Pascual Martínez-Gómez, Koji Mineshima, Daisuke Bekki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is difficult. By contrast, logical semantic representations capture deeper levels of sentence semantics, but their symbolic nature does not offer graded notions of textual similarity. We propose a method for determining semantic textual similarity by combining shallow features with features extracted from natural deduction proofs of bidirectional entailment relations between sentence pairs. For the natural deduction proofs, we use ccg2lambda, a higher-order automatic inference system, which converts Combinatory Categorial Grammar (CCG) derivation trees into semantic representations and conducts natural deduction proofs. Experiments show that our system was able to outperform other logic-based systems and that features derived from the proofs are effective for learning textual similarity.

Original languageEnglish
Title of host publicationEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages681-691
Number of pages11
ISBN (Electronic)9781945626838
DOIs
Publication statusPublished - 2017 Jan 1
Event2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark
Duration: 2017 Sep 92017 Sep 11

Publication series

NameEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
CountryDenmark
CityCopenhagen
Period17/9/917/9/11

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Fingerprint Dive into the research topics of 'Determining semantic textual similarity using natural deduction proofs'. Together they form a unique fingerprint.

  • Cite this

    Yanaka, H., Martínez-Gómez, P., Mineshima, K., & Bekki, D. (2017). Determining semantic textual similarity using natural deduction proofs. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 681-691). (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d17-1071