Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning

TL;DR

This paper introduces a novel selective adversarial learning approach for unsupervised domain adaptation in aspect-based sentiment analysis, enabling effective transfer without relying on external linguistic resources.

Contribution

It proposes a dynamic, fine-grained alignment method that automatically captures latent relations between aspects and opinions across domains.

Findings

SAL outperforms existing methods in domain adaptation tasks

The approach achieves significant improvements in sentiment extraction accuracy

Extensive experiments validate the effectiveness of the proposed method

Abstract

Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferred correlation vectors that automatically capture their latent relations. The SAL method can dynamically learn an alignment weight for each word such that more important words can possess higher alignment weights to achieve fine-grained (word-level) adaptation. Empirically, extensive experiments demonstrate the effectiveness of the proposed SAL method.