Unified Feature and Instance Based Domain Adaptation for Aspect-Based Sentiment Analysis
| Autor: | Rui Xia, Chenggong Gong, Jianfei Yu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Dependency (UML)
business.industry Computer science Sentiment analysis 02 engineering and technology Machine learning computer.software_genre Sequence labeling Domain (software engineering) Weighting Task (computing) 020204 information systems 0202 electrical engineering electronic engineering information engineering Feature (machine learning) 020201 artificial intelligence & image processing Artificial intelligence Adaptation (computer science) business computer |
| Zdroj: | EMNLP (1) |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|