当前位置:
X-MOL 学术
›
arXiv.cs.IR
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
GTN-ED: Event Detection Using Graph Transformer Networks
arXiv - CS - Information Retrieval Pub Date : 2021-04-30 , DOI: arxiv-2104.15104 Sanghamitra Dutta, Liang Ma, Tanay Kumar Saha, Di Lu, Joel Joel Tetreault, Alex Jaimes
arXiv - CS - Information Retrieval Pub Date : 2021-04-30 , DOI: arxiv-2104.15104 Sanghamitra Dutta, Liang Ma, Tanay Kumar Saha, Di Lu, Joel Joel Tetreault, Alex Jaimes
Recent works show that the graph structure of sentences, generated from
dependency parsers, has potential for improving event detection. However, they
often only leverage the edges (dependencies) between words, and discard the
dependency labels (e.g., nominal-subject), treating the underlying graph edges
as homogeneous. In this work, we propose a novel framework for incorporating
both dependencies and their labels using a recently proposed technique called
Graph Transformer Networks (GTN). We integrate GTNs to leverage dependency
relations on two existing homogeneous-graph-based models, and demonstrate an
improvement in the F1 score on the ACE dataset.
中文翻译:
GTN-ED:使用图形变压器网络进行事件检测
最近的工作表明,从依存解析器生成的句子的图结构具有改进事件检测的潜力。但是,它们通常仅利用单词之间的边缘(依赖关系),而丢弃依赖关系标签(例如,标称主题),将基础图的边缘视为同质的。在这项工作中,我们提出了一个新颖的框架,该框架使用最近提出的称为“图形变压器网络”(Graph Transformer Networks,GTN)的技术来合并依赖项及其标签。我们集成了GTN,以利用对两个现有基于均质图的模型的依赖关系,并证明ACE数据集的F1得分有所提高。
更新日期:2021-05-03
中文翻译:
GTN-ED:使用图形变压器网络进行事件检测
最近的工作表明,从依存解析器生成的句子的图结构具有改进事件检测的潜力。但是,它们通常仅利用单词之间的边缘(依赖关系),而丢弃依赖关系标签(例如,标称主题),将基础图的边缘视为同质的。在这项工作中,我们提出了一个新颖的框架,该框架使用最近提出的称为“图形变压器网络”(Graph Transformer Networks,GTN)的技术来合并依赖项及其标签。我们集成了GTN,以利用对两个现有基于均质图的模型的依赖关系,并证明ACE数据集的F1得分有所提高。