Visual Denotations for Recognizing Textual Entailment

Dan Han, Pascual Martínez-Gómez, Koji Mineshima


Abstract
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.
Anthology ID:
D17-1305
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2853–2859
Language:
URL:
https://aclanthology.org/D17-1305
DOI:
10.18653/v1/D17-1305
Bibkey:
Cite (ACL):
Dan Han, Pascual Martínez-Gómez, and Koji Mineshima. 2017. Visual Denotations for Recognizing Textual Entailment. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2853–2859, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Visual Denotations for Recognizing Textual Entailment (Han et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1305.pdf
Video:
 https://aclanthology.org/D17-1305.mp4
Data
SICKSNLI