Abstract
In this paper, we present InstructABSA, Aspect-Based Sentiment Analysis (ABSA) using instruction learning paradigm for all ABSA subtasks: Aspect Term Extraction (ATE), Aspect Term Sentiment Classification (ATSC), and Joint Task modeling. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tunes the model (Tk-Instruct Base) for each ABSA subtask, yielding significant performance improvements. Experimental results on the Sem Eval 2014 dataset demonstrate that InstructABSA outperforms the previous state-of-the-art (SOTA) approaches on all three ABSA subtasks (ATE, ATSC, and Joint Task) by a significant margin, outperforming 7x larger models. In particular, InstructABSA surpasses the SOTA on the restaurant ATE subtask by 7.31% points and on the Laptop Joint Task by 8.63% points. Our results also suggest a strong generalization ability to unseen tasks across all three subtasks.
Abstract (translated)
在本文中,我们提出了InstructABSA,一种基于 aspect 特征的情感分析(ABSA)方法,使用了指令学习范式对所有三个ABSA子任务(ate、aTSC 和联合任务建模): aspect 特征提取(ate)、 aspect 特征情感分类(aTSC)和联合任务建模。我们向每个训练样本引入了积极、消极和中性例子,并指令优化每个ABSA子任务模型(Tk-指令基础),带来了显著的性能改善。在SemEval 2014数据集的实验结果表明,InstructABSA在三个ABSA子任务(ate、aTSC 和联合任务)中比先前的先进技术方法表现得更好,比模型规模扩大了7倍。特别是,InstructABSA在餐厅 ate 子任务上超过SOTA方法7.31%,在笔记本电脑联合任务上超过8.63%。我们的结果还表明,可以在三个子任务中 unseen 任务的强大泛化能力。
URL
https://arxiv.org/abs/2302.08624
