Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them. Both the previous pipeline and integrated methods fail to precisely model the innate connection between these two objectives. In this paper, we propose a novel dynamic heterogeneous graph to jointly model the two objectives in an explicit way. Both the ordinary words and sentiment labels are treated as nodes in the heterogeneous graph, so that the aspect words can interact with the sentiment information. The graph is initialized with multiple types of dependencies, and dynamically modified during real-time prediction. Experiments on the benchmark datasets show that our model outperforms the state-of-the-art models. Further analysis demonstrates that our model obtains significant performance gain on the challenging instances under multiple-opinion aspects and no-opinion aspect situations.
翻译:基于目标的感知分析旨在检测意见方面(目的提取)和感知两极(感知检测),以前的管道和综合方法都未能精确地模拟这两个目标之间的内在联系。在本文中,我们提出一个全新的动态多元图,以明确的方式共同模拟这两个目标。普通单词和感知标签都被视为多元图中的节点,以便内容单词能够与感知信息互动。图表以多种依赖形式初始化,并在实时预测期间动态地修改。基准数据集实验显示,我们的模型优于最先进的模型。进一步的分析表明,我们的模型在多重观察和不观察情况下具有挑战性的情况中取得了显著的绩效收益。