Large Language Models Enhanced by Plug and Play Syntactic Knowledge for Aspect-based Sentiment Analysis

TL;DR

This paper introduces a plug-and-play syntactic knowledge module for large language models to enhance aspect-based sentiment analysis, achieving better results without extensive fine-tuning.

Contribution

It proposes a detachable memory module that incorporates syntactic knowledge into LLMs for ABSA, reducing training complexity and resource requirements.

Findings

Outperforms strong baselines on benchmark datasets

Effectively incorporates syntactic knowledge into LLMs

Demonstrates versatility and efficiency of the plugin approach

Abstract

Aspect-based sentiment analysis (ABSA) generally requires a deep understanding of the contextual information, including the words associated with the aspect terms and their syntactic dependencies. Most existing studies employ advanced encoders (e.g., pre-trained models) to capture such context, especially large language models (LLMs). However, training these encoders is resource-intensive, and in many cases, the available data is insufficient for necessary fine-tuning. Therefore it is challenging for learning LLMs within such restricted environments and computation efficiency requirement. As a result, it motivates the exploration of plug-and-play methods that adapt LLMs to ABSA with minimal effort. In this paper, we propose an approach that integrates extendable components capable of incorporating various types of syntactic knowledge, such as constituent syntax, word dependencies, and combinatory categorial grammar (CCG). Specifically, we propose a memory module that records syntactic information and is incorporated into LLMs to instruct the prediction of sentiment polarities. Importantly, this encoder acts as a versatile, detachable plugin that is trained independently of the LLM. We conduct experiments on benchmark datasets, which show that our approach outperforms strong baselines and previous approaches, thus demonstrates its effectiveness.