ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks

Autor:	Xiong, Kai, Ding, Xiao, Li, Zhongyang, Du, Li, Qin, Bing, Zheng, Yi, Huai, Baoxing
Rok vydání:	2022
Předmět:	Computer Science - Artificial Intelligence Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by EMNLP 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.08322 Zobrazit plný text záznamu View this record from Arxiv