Beyond Language: Learning Commonsense from Images for Reasoning

Wanqing Cui, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng


Abstract
This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in NLP. Our motivation comes from the fact that an image is worth a thousand words, where richer scene information could be leveraged to help distill the commonsense knowledge, which is often hidden in languages. Our approach, namely Loire, consists of two stages. In the first stage, a bi-modal sequence-to-sequence approach is utilized to conduct the scene layout generation task, based on a text representation model ViBERT. In this way, the required visual scene knowledge, such as spatial relations, will be encoded in ViBERT by the supervised learning process with some bi-modal data like COCO. Then ViBERT is concatenated with a pre-trained language model to perform the downstream commonsense reasoning tasks. Experimental results on two commonsense reasoning problems, i.e.commonsense question answering and pronoun resolution, demonstrate that Loire outperforms traditional language-based methods. We also give some case studies to show what knowledge is learned from images and explain how the generated scene layout helps the commonsense reasoning process.
Anthology ID:
2020.findings-emnlp.392
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4379–4389
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.392
DOI:
10.18653/v1/2020.findings-emnlp.392
Bibkey:
Cite (ACL):
Wanqing Cui, Yanyan Lan, Liang Pang, Jiafeng Guo, and Xueqi Cheng. 2020. Beyond Language: Learning Commonsense from Images for Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4379–4389, Online. Association for Computational Linguistics.
Cite (Informal):
Beyond Language: Learning Commonsense from Images for Reasoning (Cui et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.392.pdf
Video:
 https://slideslive.com/38940176
Code
 VickiCui/Loire
Data
COCOCommonsenseQAConceptNetWinoGrande