Enhancing Generative Aspect-Based Sentiment Analysis with Relation-Level Supervision and Prompt

Aspect-Based Sentiment Analysis (ABSA) aims to recognize fine-grained sentiments and opinions of users, which is a pivotal problem in sentiment analysis. ABSA research generally involves four fundamental sentiment elements: aspect term, opinion term, aspect category, and sentiment polarity. The core challenge of ABSA lies in effectively modeling the relations between aspect and opinion terms, as these relations are crucial for accurately determining aspect categories and sentiment polarities. Consequently, researchers develop various modules to model these relations, attaining outstanding performances. Recently, generative approaches have attracted increasing attention in ABSA due to their capacity to handle various ABSA tasks in a unified manner. However, existing generative approaches do not exploit these relations, potentially limiting their performance. In this paper, we introduce two novel relation modules: Relation Supervision Module (RSM) and Relation Prompt Module (RPM) for generative ABSA approaches. These modules enhance the relation modeling capability of generative models at both encoding and decoding stages. Extensive experiments on three benchmarks demonstrate that the proposed modules significantly improve the performance of existing generative approaches.