Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning

Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji, Daisuke Bekki


Abstract
In formal logic-based approaches to Recognizing Textual Entailment (RTE), a Combinatory Categorial Grammar (CCG) parser is used to parse input premises and hypotheses to obtain their logical formulas. Here, it is important that the parser processes the sentences consistently; failing to recognize the similar syntactic structure results in inconsistent predicate argument structures among them, in which case the succeeding theorem proving is doomed to failure. In this work, we present a simple method to extend an existing CCG parser to parse a set of sentences consistently, which is achieved with an inter-sentence modeling with Markov Random Fields (MRF). When combined with existing logic-based systems, our method always shows improvement in the RTE experiments on English and Japanese languages.
Anthology ID:
N18-2065
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
407–412
Language:
URL:
https://aclanthology.org/N18-2065
DOI:
10.18653/v1/N18-2065
Bibkey:
Cite (ACL):
Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji, and Daisuke Bekki. 2018. Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 407–412, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning (Yoshikawa et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2065.pdf
Data
SICK