Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs
Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs
复制标题
DOI：
10.18653/v1/d19-1498
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Fenia Christopoulou;Makoto Miwa;S. Ananiadou
中科院分区：
文献类型：
--
作者：
Fenia Christopoulou;Makoto Miwa;S. Ananiadou
文档级关系提取是一个复杂的人工过程，需要逻辑推理来提取文本中命名实体之间的关系。现有的方法使用基于图的神经模型，将单词作为节点，将边作为它们之间的关系，来编码句子之间的关系。这些模型是基于节点的，也就是说，它们形成仅基于两个目标节点表示的成对表示。然而，实体关系可以通过作为节点之间路径形成的唯一边缘表示来更好地表达。因此，我们提出了一个面向边缘的图神经模型用于文档级关系提取。该模型利用不同类型的节点和边来创建文档级图。图边缘上的推理机制可以通过内部的多实例学习来学习句子内和句子间的关系。在化学疾病和基因疾病关联的两个文档级生物医学数据集上的实验表明了所提出的边缘导向方法的有效性。
Document-level relation extraction is a complex human process that requires logical inference to extract relationships between named entities in text. Existing approaches use graph-based neural models with words as nodes and edges as relations between them, to encode relations across sentences. These models are node-based, i.e., they form pair representations based solely on the two target node representations. However, entity relations can be better expressed through unique edge representations formed as paths between nodes. We thus propose an edge-oriented graph neural model for document-level relation extraction. The model utilises different types of nodes and edges to create a document-level graph. An inference mechanism on the graph edges enables to learn intra- and inter-sentence relations using multi-instance learning internally. Experiments on two document-level biomedical datasets for chemical-disease and gene-disease associations show the usefulness of the proposed edge-oriented approach.