TY - GEN
T1 - Logical inferences with comparatives and generalized quantifiers
AU - Haruta, Izumi
AU - Mineshima, Koji
AU - Bekki, Daisuke
N1 - Funding Information:
Acknowledgments We are grateful to Hitomi Yanaka for sharing the detailed results on the MED dataset and Masashi Yoshikawa for continuous support. We also thank the three anonymous reviewers for their helpful comments and feedback. This work was supported by JSPS KAK-ENHI Grant Number JP18H03284.
Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - Comparative constructions pose a challenge in Natural Language Inference (NLI), which is the task of determining whether a text entails a hypothesis. Comparatives are structurally complex in that they interact with other linguistic phenomena such as quantifiers, numerals, and lexical antonyms. In formal semantics, there is a rich body of work on comparatives and gradable expressions using the notion of degree. However, a logical inference system for comparatives has not been sufficiently developed for use in the NLI task. In this paper, we present a compositional semantics that maps various comparative constructions in English to semantic representations via Combinatory Categorial Grammar (CCG) parsers and combine it with an inference system based on automated theorem proving. We evaluate our system on three NLI datasets that contain complex logical inferences with comparatives, generalized quantifiers, and numerals. We show that the system outperforms previous logic-based systems as well as recent deep learning-based models.
AB - Comparative constructions pose a challenge in Natural Language Inference (NLI), which is the task of determining whether a text entails a hypothesis. Comparatives are structurally complex in that they interact with other linguistic phenomena such as quantifiers, numerals, and lexical antonyms. In formal semantics, there is a rich body of work on comparatives and gradable expressions using the notion of degree. However, a logical inference system for comparatives has not been sufficiently developed for use in the NLI task. In this paper, we present a compositional semantics that maps various comparative constructions in English to semantic representations via Combinatory Categorial Grammar (CCG) parsers and combine it with an inference system based on automated theorem proving. We evaluate our system on three NLI datasets that contain complex logical inferences with comparatives, generalized quantifiers, and numerals. We show that the system outperforms previous logic-based systems as well as recent deep learning-based models.
UR - http://www.scopus.com/inward/record.url?scp=85099204273&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099204273&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85099204273
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 263
EP - 270
BT - ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
PB - Association for Computational Linguistics (ACL)
T2 - 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Student Research Workshop, SRW 2020
Y2 - 5 July 2020 through 10 July 2020
ER -