TY - GEN
T1 - Consistent CCG parsing over multiple sentences for improved logical reasoning
AU - Yoshikawa, Masashi
AU - Mineshima, Koji
AU - Noji, Hiroshi
AU - Bekki, Daisuke
N1 - Funding Information:
First of all, we thank the three anonymous reviewers for their insightful comments. We are also grateful to Lasha Abzianidze for conducting in-depth experiments and for detailed discussion about LangPro. This work was supported by JST CREST Grant Number JPMJCR1301, Japan.
Publisher Copyright:
© 2018 Association for Computational Linguistics.
PY - 2018
Y1 - 2018
N2 - 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 a 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.
AB - 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 a 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.
UR - http://www.scopus.com/inward/record.url?scp=85083509760&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083509760&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85083509760
T3 - NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
SP - 407
EP - 412
BT - Short Papers
PB - Association for Computational Linguistics (ACL)
T2 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
Y2 - 1 June 2018 through 6 June 2018
ER -