ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929590016933888 |
|---|---|
| author | Xiong, Kai Ding, Xiao Li, Zhongyang Du, Li Qin, Bing Zheng, Yi Huai, Baoxing |
| author_facet | Xiong, Kai Ding, Xiao Li, Zhongyang Du, Li Qin, Bing Zheng, Yi Huai, Baoxing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_08322 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks Xiong, Kai Ding, Xiao Li, Zhongyang Du, Li Qin, Bing Zheng, Yi Huai, Baoxing Artificial Intelligence Computation and Language 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. |
| title | ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2212.08322 |