Explainable Question Answering based on Semantic Graph by Global Differentiable Learning and Dynamic Adaptive Reasoning
Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Hong Liu, Yu Xia, Yajuan Lyu, QiaoQiao She
Abstract
Multi-hop Question Answering is an agent task for testing the reasoning ability. With the development of pre-trained models, the implicit reasoning ability has been surprisingly improved and can even surpass human performance. However, the nature of the black box hinders the construction of explainable intelligent systems. Several researchers have explored explainable neural-symbolic reasoning methods based on question decomposition techniques. The undifferentiable symbolic operations and the error propagation in the reasoning process lead to poor performance. To alleviate it, we propose a simple yet effective Global Differentiable Learning strategy to explore optimal reasoning paths from the latent probability space so that the model learns to solve intermediate reasoning processes without expert annotations. We further design a Dynamic Adaptive Reasoner to enhance the generalization of unseen questions. Our method achieves 17% improvements in F1-score against BreakRC and shows better interpretability. We take a step forward in building interpretable reasoning methods.- Anthology ID:
- 2022.emnlp-main.356
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5318–5325
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2022.emnlp-main.356/
- DOI:
- 10.18653/v1/2022.emnlp-main.356
- Cite (ACL):
- Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Hong Liu, Yu Xia, Yajuan Lyu, and QiaoQiao She. 2022. Explainable Question Answering based on Semantic Graph by Global Differentiable Learning and Dynamic Adaptive Reasoning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5318–5325, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Explainable Question Answering based on Semantic Graph by Global Differentiable Learning and Dynamic Adaptive Reasoning (Mao et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2022.emnlp-main.356.pdf