In this paper, we present InstructABSA, Aspect Based Sentiment Analysis (ABSA) using the 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) for each ABSA subtask, yielding significant performance improvements. Experimental results on the Sem Eval 2014, 15, and 16 datasets 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 Rest14 ATE subtask by 7.31% points, Rest15 ATSC subtask by and on the Lapt14 Joint Task by 8.63% points. Our results also suggest a strong generalization ability to new domains across all three subtasks
翻译：在本文中，我们提出了 InstructABSA，一种使用指示学习范例对所有 ABSA 子任务（方面提取、方面情感分类和联合任务建模）进行的方面情感分析（ABSA）。 我们的方法为每个训练样本引入了积极、消极和中性示例，并通过指示调整模型（Tk-Instruct）用于每个 ABFS 子任务，从而显着提高了性能。 在 Sem Eval 2014、15 和 16 数据集上的实验结果表明，InstructABSA 在所有三个 ABSA 子任务 (ATE、ATSC 和 Joint Task) 上都优于先前的最先进 (SOTA) 方法，超越 7 倍更大的模型。 特别是，在 Rest14 ATE 子任务上，InstructABSA 的表现超过了 SOTA 7.31%，在 Rest15 ATSC 子任务上，在 Lapt14 Joint Task 上分别超过了 8.63%。 我们的结果还表明了三个子任务在新领域具有很强的泛化能力。
相关内容
微信扫码咨询专知VIP会员