Document-level relation extraction is to extract relation facts from a document consisting of multiple sentences, in which pronoun crossed sentences are a ubiquitous phenomenon against a single sentence. However, most of the previous works focus more on mentions coreference resolution except for pronouns, and rarely pay attention to mention-pronoun coreference and capturing the relations. To represent multi-sentence features by pronouns, we imitate the reading process of humans by leveraging coreference information when dynamically constructing a heterogeneous graph to enhance semantic information. Since the pronoun is notoriously ambiguous in the graph, a mention-pronoun coreference resolution is introduced to calculate the affinity between pronouns and corresponding mentions, and the noise suppression mechanism is proposed to reduce the noise caused by pronouns. Experiments on the public dataset, DocRED, DialogRE and MPDD, show that Coref-aware Doc-level Relation Extraction based on Graph Inference Network outperforms the state-of-the-art.
翻译:文件级关系提取是为了从由多个句子组成的文件中提取关系事实,在该文件中,代名词跨过的句子是对一个单句的无处不在的现象。然而,前几部著作大多更侧重于提及除代名词以外的共同参考分辨率,而很少注意提及-pronoun 共同参照和捕捉关系。为了通过代名词代表多重发音特征,我们模仿人类的阅读过程,在动态构建多元图以强化语义信息时利用共同参考信息。由于在图表中代名词模糊不清,因此引入了提及-Pronoun 引用法,以计算代名词和相应提及词之间的亲近性,并提议噪音抑制机制以减少代名词引起的噪音。在公共数据集上进行的实验,Docred、 DialogRE和MPD显示,基于图义网络的Corf-awareal Tricon Explicon超越了该状态。