论文标题
Unifiedabsa：基于多任务指令调整的统一ABSA框架
UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning
论文作者
论文摘要
基于方面的情感分析（ABSA）旨在提供细粒度的方面级别信息。有许多ABSA任务，当前的主要范式是为每个任务培训特定于任务的模型。但是，ABSA任务的应用程序场景通常是多种多样的。该解决方案通常需要每个任务中的大量标记数据才能表现出色。这些专用的模型分别训练并分别预测，忽略了任务之间的关系。为了解决这些问题，我们提出了基于多任务指令调整的通用ABSA框架UnifiedAbsa，它可以统一地对各种任务进行建模并通过多任务学习捕获任务范围的依赖性。在两个基准数据集上进行的广泛实验表明，Unifiedabsa可以在11个ABSA任务上大大优于专用模型，并在数据效率方面表现出优势。
Aspect-Based Sentiment Analysis (ABSA) aims to provide fine-grained aspect-level sentiment information. There are many ABSA tasks, and the current dominant paradigm is to train task-specific models for each task. However, application scenarios of ABSA tasks are often diverse. This solution usually requires a large amount of labeled data from each task to perform excellently. These dedicated models are separately trained and separately predicted, ignoring the relationship between tasks. To tackle these issues, we present UnifiedABSA, a general-purpose ABSA framework based on multi-task instruction tuning, which can uniformly model various tasks and capture the inter-task dependency with multi-task learning. Extensive experiments on two benchmark datasets show that UnifiedABSA can significantly outperform dedicated models on 11 ABSA tasks and show its superiority in terms of data efficiency.
