arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.07510cs.CLcs.LG
收藏

用于关系抽取的注意力引导图卷积网络

Attention Guided Graph Convolutional Networks for Relation Extraction

Singapore University of Technology and Design(新加坡科技设计大学)

Zhijiang Guo, Yan Zhang, Wei Lu

摘要:

依赖树传递了丰富的结构信息,这些信息被证明对于提取文本中实体之间的关系非常有用。然而,如何有效地利用相关信息,而忽略无关信息的依赖树仍然是一个具有挑战性的研究问题。采用基于规则的硬修剪策略来选择相关部分依赖结构的现有方法可能并不总是产生最佳结果。在这项工作中,我们提出了注意力引导的图卷积网络(AGGCN),一种新的模型,它直接采取全依赖树作为输入。我们的模型可以被理解为一个软修剪的方法,自动学习如何有选择地参加相关的子结构有用的关系抽取任务。在跨句子n元关系抽取和大规模的文档级关系抽取等任务上的广泛结果表明,我们的模型能够更好地利用完整依赖树的结构信息,比以前的方法给出了更好的结果。

英文摘要:

Dependency trees convey rich structural information that is proven useful for extracting relations among entities in text. However, how to effectively make use of relevant information while ignoring irrelevant information from the dependency trees remains a challenging research question. Existing approaches employing rule based hard-pruning strategies for selecting relevant partial dependency structures may not always yield optimal results. In this work, we propose Attention Guided Graph Convolutional Networks (AGGCNs), a novel model which directly takes full dependency trees as inputs. Our model can be understood as a soft-pruning approach that automatically learns how to selectively attend to the relevant sub-structures useful for the relation extraction task. Extensive results on various tasks including cross-sentence n-ary relation extraction and large-scale sentence-level relation extraction show that our model is able to better leverage the structural information of the full dependency trees, giving significantly better results than previous approaches.

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。

↑