论文标题
统一标签空间以进行方面和基于句子的情感分析
Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
论文作者
论文摘要
基于方面的情感分析（ABSA）是一项精细的任务，旨在确定对句子中发生的目标方面术语的情感极性。缺乏带注释的数据，ABSA任务的发展极大地阻碍了。为了解决这个问题，先前的作品研究了利用情感分析（SA）数据集的可能性，主要是通过预训练或多任务学习来培训ABSA模型。在本文中，我们遵循这一行，这是我们首次设法应用伪标签方法（PL）方法来合并这两个均匀任务。虽然使用生成的伪标签来处理这两个高度相关任务的标签粒度统一，但我们在本文中确定了它的主要挑战，并提出了一个新颖的框架，称为双重粒度伪标签（DPL），这似乎很简单。此外，类似于PL，我们将DPL视为能够结合文献中其他先前方法的一般框架。通过广泛的实验，DPL在标准基准测试基准上实现了最先进的工作，超过了先前的工作。
The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence. The development of the ABSA task is very much hindered by the lack of annotated data. To tackle this, the prior works have studied the possibility of utilizing the sentiment analysis (SA) datasets to assist in training the ABSA model, primarily via pretraining or multi-task learning. In this article, we follow this line, and for the first time, we manage to apply the Pseudo-Label (PL) method to merge the two homogeneous tasks. While it seems straightforward to use generated pseudo labels to handle this case of label granularity unification for two highly related tasks, we identify its major challenge in this paper and propose a novel framework, dubbed as Dual-granularity Pseudo Labeling (DPL). Further, similar to PL, we regard the DPL as a general framework capable of combining other prior methods in the literature. Through extensive experiments, DPL has achieved state-of-the-art performance on standard benchmarks surpassing the prior work significantly.
