面向少样本基于方面的情感分析的指令微调
Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis
AI总结：
本研究针对少样本场景下的基于方面的情感分析任务，提出基于指令提示的T5多任务微调统一框架，覆盖全部子任务与四元组预测，在多个基准上实现F1绝对提升8.29。
摘要：
基于方面的情感分析（Aspect-based Sentiment Analysis, ABSA）是一项细粒度的情感分析任务，涉及用户生成文本中的四个要素：方面词、方面类别、观点词和情感极性。大多数计算方法聚焦于部分ABSA子任务，例如使用流水线或联合建模方法提取二元组（方面词，情感极性）或三元组（方面词，观点词，情感极性）。近期，已有研究提出生成式方法，将提取全部四个要素的（一个或多个）四元组作为单一任务从文本中完成。在本研究中，我们进一步提出一个统一框架用于求解ABSA及其相关子任务，以提升少样本场景下的性能。为此，我们以多任务学习的方式，使用指令提示对T5模型进行微调，覆盖所有子任务以及完整的四元组预测任务。在多个基准数据集上的实验表明，所提出的多任务提示方法在少样本学习设置下带来了性能提升（F1值绝对提升8.29）。
英文摘要：
Aspect-based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task which involves four elements from user-generated texts: aspect term, aspect category, opinion term, and sentiment polarity. Most computational approaches focus on some of the ABSA sub-tasks such as tuple (aspect term, sentiment polarity) or triplet (aspect term, opinion term, sentiment polarity) extraction using either pipeline or joint modeling approaches. Recently, generative approaches have been proposed to extract all four elements as (one or more) quadruplets from text as a single task. In this work, we take a step further and propose a unified framework for solving ABSA, and the associated sub-tasks to improve the performance in few-shot scenarios. To this end, we fine-tune a T5 model with instructional prompts in a multi-task learning fashion covering all the sub-tasks, as well as the entire quadruple prediction task. In experiments with multiple benchmark datasets, we show that the proposed multi-task prompting approach brings performance boost (by absolute 8.29 F1) in the few-shot learning setting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
