TY - GEN
T1 - Visual denotations for recognizing textual entailment
AU - Han, Dan
AU - Martínez-Gómez, Pascual
AU - Mineshima, Koji
N1 - Funding Information:
This paper is based on results obtained from a project commissioned by the New Energy and Industrial Technology Development Organization (NEDO). This project is also supported by JSPS KAKENHI Grant Number 17K12747, partially funded by Microsoft Research Asia and JST CREST Grant Number JPMJCR1301, Japan. We thank Ola Vikholt and the anonymous reviewers for their valuable comments.
Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - In the logic approach to Recognizing Textual Entailment, identifying phrase-to-phrase semantic relations is still an unsolved problem. Resources such as the Paraphrase Database offer limited coverage despite their large size whereas unsupervised distributional models of meaning often fail to recognize phrasal entailments. We propose to map phrases to their visual denotations and compare their meaning in terms of their images. We show that our approach is effective in the task of Recognizing Textual Entailment when combined with specific linguistic and logic features.
AB - In the logic approach to Recognizing Textual Entailment, identifying phrase-to-phrase semantic relations is still an unsolved problem. Resources such as the Paraphrase Database offer limited coverage despite their large size whereas unsupervised distributional models of meaning often fail to recognize phrasal entailments. We propose to map phrases to their visual denotations and compare their meaning in terms of their images. We show that our approach is effective in the task of Recognizing Textual Entailment when combined with specific linguistic and logic features.
UR - http://www.scopus.com/inward/record.url?scp=85073144897&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073144897&partnerID=8YFLogxK
U2 - 10.18653/v1/d17-1305
DO - 10.18653/v1/d17-1305
M3 - Conference contribution
AN - SCOPUS:85073144897
T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 2853
EP - 2859
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 -