《A walk-based Model on Entity Graphs for Relational Extraction》

• 下载地址：http://arxiv.org/pdf/1902.07023v1.pdf
• 本文在进行关系提取时会考虑不同实体关系之间的传递性、关联性，并借此对实体之间的关系进行建模。
  -当一句话中存在多种关系时，不同关系之间往往会存在一定的联系，即目标实体对之间的关系可能会收到该句中其他实体间的关系。现有的大多数RE模型往往会忽略这种问题。
  摘要：We present a novel graph-based neural network model for relation extraction. Our model treats multiple pairs in a sentence simultaneously and considers interactions among them. All the entities in a sentence are placed as nodes in a fully-connected graph structure. The edges are represented with position-aware contexts around the entity pairs. In order to consider different relation paths between two entities, we construct up to l-length walks between each pair. The resulting walks are merged and iteratively used to update the edge representations into longer walks representations. We show that the model achieves performance comparable to the state-ofthe-art systems on the ACE 2005 dataset without using any external tools.