Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis

TL;DR

This paper introduces SDAM, a syntax-guided model for cross-domain aspect-based sentiment analysis that leverages syntactic structures and a novel BERT masking approach to improve transferability and performance.

Contribution

The paper proposes a novel syntax-guided domain adaptation model, SDAM, which explicitly relates aspect terms to sentiments and captures domain-invariant features for better cross-domain ABSA.

Findings

SDAM outperforms state-of-the-art baselines on five benchmark datasets.

The syntax-based BERT mask enhances domain-invariant feature learning.

Explicitly modeling aspect-sentiment relations improves cross-domain transfer.

Abstract

Aspect-based sentiment analysis (ABSA) aims at extracting opinionated aspect terms in review texts and determining their sentiment polarities, which is widely studied in both academia and industry. As a fine-grained classification task, the annotation cost is extremely high. Domain adaptation is a popular solution to alleviate the data deficiency issue in new domains by transferring common knowledge across domains. Most cross-domain ABSA studies are based on structure correspondence learning (SCL), and use pivot features to construct auxiliary tasks for narrowing down the gap between domains. However, their pivot-based auxiliary tasks can only transfer knowledge of aspect terms but not sentiment, limiting the performance of existing models. In this work, we propose a novel Syntax-guided Domain Adaptation Model, named SDAM, for more effective cross-domain ABSA. SDAM exploits syntactic structure similarities for building pseudo training instances, during which aspect terms of target domain are explicitly related to sentiment polarities. Besides, we propose a syntax-based BERT mask language model for further capturing domain-invariant features. Finally, to alleviate the sentiment inconsistency issue in multi-gram aspect terms, we introduce a span-based joint aspect term and sentiment analysis module into the cross-domain End2End ABSA. Experiments on five benchmark datasets show that our model consistently outperforms the state-of-the-art baselines with respect to Micro-F1 metric for the cross-domain End2End ABSA task.