TY - GEN
T1 - Determining semantic textual similarity using natural deduction proofs
AU - Yanaka, Hitomi
AU - Martínez-Gómez, Pascual
AU - Mineshima, Koji
AU - Bekki, Daisuke
N1 - Funding Information:
We thank the three anonymous reviewers for their detailed comments. This work was supported by JST CREST Grant Number JPMJCR1301, Japan.
Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85044474705&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044474705&partnerID=8YFLogxK
U2 - 10.18653/v1/d17-1071
DO - 10.18653/v1/d17-1071
M3 - Conference contribution
AN - SCOPUS:85044474705
T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 681
EP - 691
BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Y2 - 9 September 2017 through 11 September 2017
ER -