Logical Inferences with Comparatives and Generalized Quantifiers

Izumi Haruta, Koji Mineshima, Daisuke Bekki


Abstract
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.
Anthology ID:
2020.acl-srw.35
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2020
Address:
Online
Editors:
Shruti Rijhwani, Jiangming Liu, Yizhong Wang, Rotem Dror
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
263–270
Language:
URL:
https://aclanthology.org/2020.acl-srw.35
DOI:
10.18653/v1/2020.acl-srw.35
Bibkey:
Cite (ACL):
Izumi Haruta, Koji Mineshima, and Daisuke Bekki. 2020. Logical Inferences with Comparatives and Generalized Quantifiers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 263–270, Online. Association for Computational Linguistics.
Cite (Informal):
Logical Inferences with Comparatives and Generalized Quantifiers (Haruta et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-srw.35.pdf
Video:
 http://slideslive.com/38928678
Code
 izumi-h/ccgcomp
Data
MEDMultiNLISNLI