Multimodal Logical Inference System for Visual-Textual Entailment
Riko Suzuki, Hitomi Yanaka, Masashi Yoshikawa, Koji Mineshima, Daisuke Bekki
Abstract
A large amount of research about multimodal inference across text and vision has been recently developed to obtain visually grounded word and sentence representations. In this paper, we use logic-based representations as unified meaning representations for texts and images and present an unsupervised multimodal logical inference system that can effectively prove entailment relations between them. We show that by combining semantic parsing and theorem proving, the system can handle semantically complex sentences for visual-textual inference.- Anthology ID:
- P19-2054
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Fernando Alva-Manchego, Eunsol Choi, Daniel Khashabi
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 386–392
- Language:
- URL:
- https://aclanthology.org/P19-2054
- DOI:
- 10.18653/v1/P19-2054
- Cite (ACL):
- Riko Suzuki, Hitomi Yanaka, Masashi Yoshikawa, Koji Mineshima, and Daisuke Bekki. 2019. Multimodal Logical Inference System for Visual-Textual Entailment. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 386–392, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Multimodal Logical Inference System for Visual-Textual Entailment (Suzuki et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/P19-2054.pdf
- Data
- Visual Genome, Visual Question Answering