Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis

Siyin Wang, Jie Zhou, Qin Chen, Qi Zhang, Tao Gui, Xuanjing Huang


Abstract
Domain adaption has been widely adapted for cross-domain sentiment analysis to transfer knowledge from the source domain to the target domain. Whereas, most methods are proposed under the assumption that the target (test) domain is known, making them fail to generalize well on unknown test data that is not always available in practice. In this paper, we focus on the problem of domain generalization for cross-domain sentiment analysis. Specifically, we propose a backdoor adjustment-based causal model to disentangle the domain-specific and domain-invariant representations that play essential roles in tackling domain shift. First, we rethink the cross-domain sentiment analysis task in a causal view to model the causal-and-effect relationships among different variables. Then, to learn an invariant feature representation, we remove the effect of domain confounders (e.g., domain knowledge) using the backdoor adjustment. A series of experiments over many homologous and diverse datasets show the great performance and robustness of our model by comparing it with the state-of-the-art domain generalization baselines.
Anthology ID:
2024.lrec-main.470
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
5286–5298
Language:
URL:
https://aclanthology.org/2024.lrec-main.470
DOI:
Bibkey:
Cite (ACL):
Siyin Wang, Jie Zhou, Qin Chen, Qi Zhang, Tao Gui, and Xuanjing Huang. 2024. Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5286–5298, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis (Wang et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.470.pdf