Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues. Existing relation extraction models may be unsatisfactory under such a conversational setting, due to the entangled logic and information sparsity issues in utterances involving multiple speakers. To this end, we introduce SOLS, a novel model which can explicitly induce speaker-oriented latent structures for better DiaRE. Specifically, we learn latent structures to capture the relationships among tokens beyond the utterance boundaries, alleviating the entangled logic issue. During the learning process, our speaker-specific regularization method progressively highlights speaker-related key clues and erases the irrelevant ones, alleviating the information sparsity issue. Experiments on three public datasets demonstrate the effectiveness of our proposed approach.
翻译:以对话为基础的关系提取(DiaRE)旨在探测对话中未结构化言论的结构信息。在这种对话环境中,现有的关系提取模式可能不能令人满意,因为在涉及多个发言者的言论中,由于逻辑和信息的广度问题缠绕不开。为此,我们引入了SOLS,这是一个新颖的模式,可以明确引导以语言为导向的潜在结构来改善DiaRE。具体地说,我们学习潜在的结构来捕捉超出语义界限的象征之间的关系,缓解纠缠不休的逻辑问题。在学习过程中,我们针对特定发言者的正规化方法逐渐突出与演讲者有关的关键线索,并消除无关的线索,缓解信息紧张问题。关于三个公共数据集的实验显示了我们拟议方法的有效性。