Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis

Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao


Abstract
Cross-domain sentiment classification aims to address the lack of massive amounts of labeled data. It demands to predict sentiment polarity on a target domain utilizing a classifier learned from a source domain. In this paper, we investigate how to efficiently apply the pre-training language model BERT on the unsupervised domain adaptation. Due to the pre-training task and corpus, BERT is task-agnostic, which lacks domain awareness and can not distinguish the characteristic of source and target domain when transferring knowledge. To tackle these problems, we design a post-training procedure, which contains the target domain masked language model task and a novel domain-distinguish pre-training task. The post-training procedure will encourage BERT to be domain-aware and distill the domain-specific features in a self-supervised way. Based on this, we could then conduct the adversarial training to derive the enhanced domain-invariant features. Extensive experiments on Amazon dataset show that our model outperforms state-of-the-art methods by a large margin. The ablation study demonstrates that the remarkable improvement is not only from BERT but also from our method.
Anthology ID:
2020.acl-main.370
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4019–4028
Language:
URL:
https://aclanthology.org/2020.acl-main.370
DOI:
10.18653/v1/2020.acl-main.370
Bibkey:
Cite (ACL):
Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, and Jianxin Liao. 2020. Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4019–4028, Online. Association for Computational Linguistics.
Cite (Informal):
Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis (Du et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2020.acl-main.370.pdf
Video:
 http://slideslive.com/38928809