论文标题
方面情感三重摘要的位置感知标记
Position-Aware Tagging for Aspect Sentiment Triplet Extraction
论文作者
论文摘要
方面情感三胞胎提取（ASTE）是提取目标实体的三胞胎，其相关情绪和意见跨度解释情感的原因。现有的研究工作主要使用管道方法解决这一问题，这些方法将三重态提取过程分为几个阶段。我们的观察是，三胞胎中的三个元素彼此高度相关，这促使我们使用序列标记方法构建一个联合模型来提取此类三胞胎。但是，如何有效设计一种标记方法来提取可以捕获元素之间丰富相互作用的三胞胎是一个挑战性的研究问题。在这项工作中，我们提出了第一个端到端模型，该模型具有新颖的位置感知标记方案，该方案能够共同提取三胞胎。我们对几个现有数据集的实验结果表明，使用我们的方法共同捕获三胞胎中的元素，导致对现有方法的性能提高。我们还进行了广泛的实验，以研究模型的有效性和鲁棒性。
Aspect Sentiment Triplet Extraction (ASTE) is the task of extracting the triplets of target entities, their associated sentiment, and opinion spans explaining the reason for the sentiment. Existing research efforts mostly solve this problem using pipeline approaches, which break the triplet extraction process into several stages. Our observation is that the three elements within a triplet are highly related to each other, and this motivates us to build a joint model to extract such triplets using a sequence tagging approach. However, how to effectively design a tagging approach to extract the triplets that can capture the rich interactions among the elements is a challenging research question. In this work, we propose the first end-to-end model with a novel position-aware tagging scheme that is capable of jointly extracting the triplets. Our experimental results on several existing datasets show that jointly capturing elements in the triplet using our approach leads to improved performance over the existing approaches. We also conducted extensive experiments to investigate the model effectiveness and robustness.
