Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914689185742848 |
|---|---|
| author | Wang, Siyin Zhou, Jie Chen, Qin Zhang, Qi Gui, Tao Huang, Xuanjing |
| author_facet | Wang, Siyin Zhou, Jie Chen, Qin Zhang, Qi Gui, Tao Huang, Xuanjing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14536 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis Wang, Siyin Zhou, Jie Chen, Qin Zhang, Qi Gui, Tao Huang, Xuanjing Computation and Language 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. |
| title | Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.14536 |