arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.07023cs.CL
收藏

基于Walk的实体图关系抽取模型

A Walk-based Model on Entity Graphs for Relation Extraction

National Centre for Text Mining(国家文本挖掘中心);School of Computer Science, The University of Manchester, United Kingdom(曼彻斯特大学计算机科学学院);Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST), Japan(日本先进工业科学技术研究所人工智能研究中心);Toyota Technological Institute, Nagoya, 468-8511, Japan(丰田工业大学)

Fenia Christopoulou, Makoto Miwa, Sophia Ananiadou

摘要:

我们提出了一种新的基于图的神经网络模型来进行关系抽取。我们的模型同时处理一个句子中的多个对,并考虑它们之间的相互作用。句子中的所有实体都被放置为全连接图结构中的节点。边缘用实体对周围的位置感知上下文来表示。为了考虑两个实体之间的不同关系路径,我们在每对实体之间构建l长度的路径。合并并迭代使用所产生的行走,以将边表示更新为更长的行走表示。我们表明,该模型实现的性能媲美ACE 2005数据集上的最先进的系统,而不使用任何外部工具。

英文摘要:

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-of-the-art systems on the ACE 2005 dataset without using any external tools.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑