Neural Natural Logic Inference for Interpretable Question Answering

Jihao Shi, Xiao Ding, Li Du, Ting Liu, Bing Qin


Abstract
Many open-domain question answering problems can be cast as a textual entailment task, where a question and candidate answers are concatenated to form hypotheses. A QA system then determines if the supporting knowledge bases, regarded as potential premises, entail the hypotheses. In this paper, we investigate a neural-symbolic QA approach that integrates natural logic reasoning within deep learning architectures, towards developing effective and yet explainable question answering models. The proposed model gradually bridges a hypothesis and candidate premises following natural logic inference steps to build proof paths. Entailment scores between the acquired intermediate hypotheses and candidate premises are measured to determine if a premise entails the hypothesis. As the natural logic reasoning process forms a tree-like, hierarchical structure, we embed hypotheses and premises in a Hyperbolic space rather than Euclidean space to acquire more precise representations. Empirically, our method outperforms prior work on answering multiple-choice science questions, achieving the best results on two publicly available datasets. The natural logic inference process inherently provides evidence to help explain the prediction process.
Anthology ID:
2021.emnlp-main.298
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3673–3684
Language:
URL:
https://aclanthology.org/2021.emnlp-main.298
DOI:
10.18653/v1/2021.emnlp-main.298
Bibkey:
Cite (ACL):
Jihao Shi, Xiao Ding, Li Du, Ting Liu, and Bing Qin. 2021. Neural Natural Logic Inference for Interpretable Question Answering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3673–3684, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Neural Natural Logic Inference for Interpretable Question Answering (Shi et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.298.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.298.mp4
Code
 shijihao/neunli