SynGen: A Syntactic Plug-and-play Module for Generative Aspect-based Sentiment Analysis

TL;DR

SynGen introduces a syntactic module for generative ABSA models that improves attention focus and achieves state-of-the-art performance with less training, by integrating syntactic bias without disrupting backbone models.

Contribution

This paper presents the first integration of syntactic information into generative ABSA frameworks through a plug-and-play module, enhancing attention accuracy and efficiency.

Findings

Achieves comparable performance to state-of-the-art models

Reduces training consumption

Maintains structural integrity of backbone models

Abstract

Aspect-based Sentiment Analysis (ABSA) is a sentiment analysis task at fine-grained level. Recently, generative frameworks have attracted increasing attention in ABSA due to their ability to unify subtasks and their continuity to upstream pre-training tasks. However, these generative models suffer from the neighboring dependency problem that induces neighboring words to get higher attention. In this paper, we propose SynGen, a plug-and-play syntactic information aware module. As a plug-in module, our SynGen can be easily applied to any generative framework backbones. The key insight of our module is to add syntactic inductive bias to attention assignment and thus direct attention to the correct target words. To the best of our knowledge, we are the first one to introduce syntactic information to generative ABSA frameworks. Our module design is based on two main principles: (1) maintaining the structural integrity of backbone PLMs and (2) disentangling the added syntactic information and original semantic information. Empirical results on four popular ABSA datasets demonstrate that SynGen enhanced model achieves a comparable performance to the state-of-the-art model with relaxed labeling specification and less training consumption.