Abstract
The supervised models for aspect-based sentiment analysis (ABSA) rely heavily on labeled data. However, fine-grained labeled data are scarce for the ABSA task. To alleviate the dependence on labeled data, prior works mainly focused on feature-based adaptation, which used the domain-shared knowledge to construct auxiliary tasks or domain adversarial learning to bridge the gap between domains, while ignored the attribute of instance-based adaptation. To resolve this limitation, we propose an end-to-end framework to jointly perform feature and instance based adaptation for the ABSA task in this paper. Based on BERT, we learn domain-invariant feature representations by using part-of-speech features and syntactic dependency relations to construct auxiliary tasks, and jointly perform word-level instance weighting in the framework of sequence labeling. Experiment results on four benchmarks show that the proposed method can achieve significant improvements in comparison with the state-of-the-arts in both tasks of cross-domain End2End ABSA and cross-domain aspect extraction.- Anthology ID:
- 2020.emnlp-main.572
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7035–7045
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.572
- DOI:
- 10.18653/v1/2020.emnlp-main.572
- Cite (ACL):
- Chenggong Gong, Jianfei Yu, and Rui Xia. 2020. Unified Feature and Instance Based Domain Adaptation for Aspect-Based Sentiment Analysis. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7035–7045, Online. Association for Computational Linguistics.
- Cite (Informal):
- Unified Feature and Instance Based Domain Adaptation for Aspect-Based Sentiment Analysis (Gong et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2020.emnlp-main.572.pdf