Abstract
We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing works ignore the complicated reasoning process and solve it with a one-step “black box” model. Inspired by human cognitive processes, in this paper we propose a sequential approach for this task which explicitly models each step of the reasoning process with neural network modules. In particular, five reasoning modules are designed and learned in an end-to-end manner, which leads to a more interpretable model. Experimental results on the ROPES dataset demonstrate the effectiveness and explainability of our proposed approach.- Anthology ID:
- 2020.emnlp-main.548
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6745–6758
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.548
- DOI:
- 10.18653/v1/2020.emnlp-main.548
- Cite (ACL):
- Mucheng Ren, Xiubo Geng, Tao Qin, Heyan Huang, and Daxin Jiang. 2020. Towards Interpretable Reasoning over Paragraph Effects in Situation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6745–6758, Online. Association for Computational Linguistics.
- Cite (Informal):
- Towards Interpretable Reasoning over Paragraph Effects in Situation (Ren et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2020.emnlp-main.548.pdf
- Code
- Borororo/interpretable_ropes
- Data
- ROPES