Given comparative text, comparative relation extraction aims to extract two targets (\eg two cameras) in comparison and the aspect they are compared for (\eg image quality). The extracted comparative relations form the basis of further opinion analysis.Existing solutions formulate this task as a sequence labeling task, to extract targets and aspects. However, they cannot directly extract comparative relation(s) from text. In this paper, we show that comparative relations can be directly extracted with high accuracy, by generative model. Based on GPT-2, we propose a Generation-based Comparative Relation Extractor (GCRE-GPT). Experiment results show that \modelname achieves state-of-the-art accuracy on two datasets.

翻译：给定比较性文本，比较关系抽取的目标是抽取出被比较的两个目标（例如两款相机）以及它们被比较的方面（例如图像质量）。所抽取出的比较关系构成了进一步观点分析的基础。现有解决方案将此项任务构建为序列标注任务，以抽取目标与方面。然而，这些方法无法直接从文本中抽取比较关系。在本文中，我们证明通过生成式模型可以直接且高精度地抽取比较关系。基于GPT-2，我们提出了一种基于生成的比较关系抽取器（GCRE-GPT）。实验结果表明，\modelname 在两个数据集上均达到了最先进的准确率。