Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis

Hui Wu, Xiaodong Shi


Abstract
Cross-domain sentiment analysis has achieved promising results with the help of pre-trained language models. As GPT-3 appears, prompt tuning has been widely explored to enable better semantic modeling in many natural language processing tasks. However, directly using a fixed predefined template for cross-domain research cannot model different distributions of the \operatorname{[MASK]} token in different domains, thus making underuse of the prompt tuning technique. In this paper, we propose a novel Adversarial Soft Prompt Tuning method (AdSPT) to better model cross-domain sentiment analysis. On the one hand, AdSPT adopts separate soft prompts instead of hard templates to learn different vectors for different domains, thus alleviating the domain discrepancy of the \operatorname{[MASK]} token in the masked language modeling task. On the other hand, AdSPT uses a novel domain adversarial training strategy to learn domain-invariant representations between each source domain and the target domain. Experiments on a publicly available sentiment analysis dataset show that our model achieves the new state-of-the-art results for both single-source domain adaptation and multi-source domain adaptation.
Anthology ID:
2022.acl-long.174
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2438–2447
Language:
URL:
https://aclanthology.org/2022.acl-long.174
DOI:
10.18653/v1/2022.acl-long.174
Bibkey:
Cite (ACL):
Hui Wu and Xiaodong Shi. 2022. Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2438–2447, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis (Wu & Shi, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.174.pdf