Title | ||
---|---|---|
Adaptive Pre-Training and Collaborative Fine-Tuning: A Win-Win Strategy to Improve Review Analysis Tasks |
Abstract | ||
---|---|---|
Summarizing user reviews and classifying user sentiment are two critical tasks for modern e-commerce platforms. These two tasks can benefit each other by capturing the shared linguistic features. However, such a relationship has not been fully exploited by existing research on domain-specific contextual representations. This work explores a win-win strategy for a multi-task framework with three stages: general pre-training, adaptive pre-training, and collaborative fine-tuning. The task-adaptive continual pre-training on a language model can obtain domain-specific contextual representations, further used to improve two related tasks, sentiment classification and review summarization during the collaborative fine-tuning. Meanwhile, to effectively capture sentiment-oriented domain-specific contextual representations, we introduce a novel task-adaptive pre-training procedure, which adds a sentiment prediction task during the adaptive pre-training. Extensive experiments conducted on two adaption scenarios of a general-to-single domain and a general-to-multiple domain show that our framework outperforms state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TASLP.2022.3140482 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | DocType | Volume |
Pre-training,review analysis,review summarization,RoBERTa,sentiment classification,task-adaptive | Journal | 30 |
Issue | ISSN | Citations |
1 | 2329-9290 | 0 |
PageRank | References | Authors |
0.34 | 13 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qianren Mao | 1 | 0 | 0.34 |
Jianxin Li | 2 | 725 | 92.14 |
Chuang Lin | 3 | 3040 | 390.74 |
Congwen Chen | 4 | 0 | 0.34 |
Hao Peng | 5 | 167 | 27.72 |
Lihong V Wang | 6 | 194 | 58.39 |
Philip S. Yu | 7 | 30670 | 3474.16 |