ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
Kai Xiong, Xiao Ding, Zhongyang Li, Li Du, Ting Liu, Bing Qin, Yi Zheng, Baoxing Huai
Abstract
Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting causal pairs. However, CCR suffers from two main transitive problems: threshold effect and scene drift. In other words, the causal pairs to be spliced may have a conflicting threshold boundary or scenario. To address these issues, we propose a novel Reliable Causal chain reasoning framework (ReCo), which introduces exogenous variables to represent the threshold and scene factors of each causal pair within the causal chain, and estimates the threshold and scene contradictions across exogenous variables via structural causal recurrent neural networks (SRNN). Experiments show that ReCo outperforms a series of strong baselines on both Chinese and English CCR datasets. Moreover, by injecting reliable causal chain knowledge distilled by ReCo, BERT can achieve better performances on four downstream causal-related tasks than BERT models enhanced by other kinds of knowledge.- Anthology ID:
- 2022.emnlp-main.431
- 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:
- 6426–6438
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.431
- DOI:
- 10.18653/v1/2022.emnlp-main.431
- Cite (ACL):
- Kai Xiong, Xiao Ding, Zhongyang Li, Li Du, Ting Liu, Bing Qin, Yi Zheng, and Baoxing Huai. 2022. ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6426–6438, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks (Xiong et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.emnlp-main.431.pdf