Aspect-based sentiment analysis (ABSA) aims to identify four sentiment elements, including aspect term, aspect category, opinion term, and sentiment polarity. These elements construct a complete picture of sentiments. The most challenging task, aspect sentiment quad prediction (ASQP), requires predicting all four elements simultaneously and is hindered by the difficulty of accurately modeling dependencies among sentiment elements. A key challenge lies in the scarcity of annotated data, which limits the model ability to understand and reason about the relational dependencies required for effective quad prediction. To address this challenge, we propose a stepwise task augmentation framework with relation learning that decomposes ASQP into a sequence of auxiliary subtasks with increasing relational granularity. Specifically, STAR incrementally constructs auxiliary data by augmenting the training data with pairwise and overall relation tasks, enabling the model to capture and compose sentiment dependencies in a stepwise manner. This stepwise formulation provides effective relational learning signals that enhance quad prediction performance, particularly in low-resource scenarios. Extensive experiments across four benchmark datasets demonstrate that STAR consistently outperforms existing methods, achieving average F1 improvements of over $2\%$ under low-resource conditions.

翻译：方面级情感分析旨在识别四个情感要素，包括方面词、方面类别、观点词和情感极性。这些要素构建了情感的完整图景。最具挑战性的任务——方面情感四元组预测，需要同时预测所有四个要素，其难点在于难以准确建模情感要素间的依赖关系。一个关键挑战在于标注数据的稀缺性，这限制了模型理解和推理有效四元组预测所需关系依赖的能力。为解决这一挑战，我们提出了一种基于关系学习的逐步任务增强框架，将ASQP分解为一系列关系粒度递增的辅助子任务。具体而言，STAR通过为训练数据增强成对关系和整体关系任务，逐步构建辅助数据，使模型能够以渐进方式捕获并组合情感依赖。这种逐步构建方式提供了有效的关系学习信号，从而提升了四元组预测性能，尤其在低资源场景下更为显著。在四个基准数据集上的大量实验表明，STAR始终优于现有方法，在低资源条件下平均F1值提升超过$2\%$。