Causal Intervention for Abstractive Related Work Generation

Jiachang Liu, Qi Zhang, Chongyang Shi, Usman Naseem, Shoujin Wang, Liang Hu, Ivor Tsang


Abstract
Abstractive related work generation has attracted increasing attention in generating coherent related work that helps readers grasp the current research. However, most existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability. In this study, we argue that causal intervention can address such limitations and improve the quality and coherence of generated related work. To this end, we propose a novel Causal Intervention Module for Related Work Generation (CaM) to effectively capture causalities in the generation process. Specifically, we first model the relations among the sentence order, document (reference) correlations, and transitional content in related work generation using a causal graph. Then, to implement causal interventions and mitigate the negative impact of spurious correlations, we use do-calculus to derive ordinary conditional probabilities and identify causal effects through CaM. Finally, we subtly fuse CaM with Transformer to obtain an end-to-end related work generation framework. Extensive experiments on two real-world datasets show that CaM can effectively promote the model to learn causal relations and thus produce related work of higher quality and coherence.
Anthology ID:
2023.findings-emnlp.141
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2148–2159
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.141
DOI:
10.18653/v1/2023.findings-emnlp.141
Bibkey:
Cite (ACL):
Jiachang Liu, Qi Zhang, Chongyang Shi, Usman Naseem, Shoujin Wang, Liang Hu, and Ivor Tsang. 2023. Causal Intervention for Abstractive Related Work Generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2148–2159, Singapore. Association for Computational Linguistics.
Cite (Informal):
Causal Intervention for Abstractive Related Work Generation (Liu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.141.pdf