A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis
This addresses the need for efficient unsupervised domain adaptation in fine-grained sentiment analysis, offering a plug-and-play solution that is incremental but practical for reducing preprocessing costs.
The paper tackles the problem of expensive annotation for aspect term extraction in cross-domain aspect-based sentiment analysis by proposing a simple mutual information maximization technique that enhances any model, achieving a 4.32% average Micro-F1 improvement over state-of-the-art methods across 10 domain pairs.
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task which aims to extract the aspects from sentences and identify their corresponding sentiments. Aspect term extraction (ATE) is the crucial step for ABSA. Due to the expensive annotation for aspect terms, we often lack labeled target domain data for fine-tuning. To address this problem, many approaches have been proposed recently to transfer common knowledge in an unsupervised way, but such methods have too many modules and require expensive multi-stage preprocessing. In this paper, we propose a simple but effective technique based on mutual information maximization, which can serve as an additional component to enhance any kind of model for cross-domain ABSA and ATE. Furthermore, we provide some analysis of this approach. Experiment results show that our proposed method outperforms the state-of-the-art methods for cross-domain ABSA by 4.32% Micro-F1 on average over 10 different domain pairs. Apart from that, our method can be extended to other sequence labeling tasks, such as named entity recognition (NER).