Meta-based self-training and re-weighting for aspect-based sentiment analysis
Aspect-based sentiment analysis (ABSA) means to identify fine-grained aspects, opinions, and sentiment polarities. Recent ABSA research focuses on utilizing multi-task learning (MTL) to achieve less computational costs and better performance. However, there are certain limits in MTL-based ABSA. For...
主要な著者: | , , , , |
---|---|
その他の著者: | |
フォーマット: | Journal Article |
言語: | English |
出版事項: |
2022
|
主題: | |
オンライン・アクセス: | https://hdl.handle.net/10356/163145 |