重庆理工大学学报(自然科学) ›› 2023, Vol. 37 ›› Issue (7): 217-226.

• 信息·计算机 • 上一篇    下一篇

融合依存关系的对话关系抽取

段瑞雪,刘 鑫,张仰森   

  1. (北京信息科技大学 智能信息处理研究所,北京 100101)
  • 出版日期:2023-08-15 发布日期:2023-08-15
  • 作者简介:段瑞雪,女,博士,讲师,主要从事自然语言处理研究,Email:duanruixue@bistu.edu.Cn

Dialogue relationship extraction with dependency relation

  • Online:2023-08-15 Published:2023-08-15

摘要: 为了提高对话中实体对的关系抽取能力,将依存关系引入到异构图注意力网络中, 提出了 DEPGAT模型。首先,通过预处理层获取每个词的基本特征,然后在话语编码层实现上 下文特征的抽取,并加入依存信息进一步掌握话语结构。最后利用特征构建异构图,设计有效 的消息传递机制,从而使得更新后的对话实体对包含了整个对话的上下文信息和语法特征,以 此提高模型对实体关系抽取的能力。实验结果表明,在 DialogRE数据集上,DEPGAT模型相比 于基线模型,F1值在开发集上提高了 2.9%,在测试集上提高了 1.8%。

关键词: 实体关系抽取, 依存关系, 异构图, 自然语言处理

Abstract: In order to enhance the ability to extract entity pair relationship in dialogues, this paper proposes a DEP-GAT model by introducing dependency relation into a heterogeneous graph attention network. Initially, the basic characteristics of each word are obtained through the preprocessing layer. Subsequently, in the discourse coding layer, context features are extracted and dependency information is added to further understand the speech structure. Eventually, a heterogeneous graph is constructed by utilizing the features, and an effective message passing mechanism is designed to enable the updated dialogue entity pairs to contain all the context information and grammatical features of the entire dialogue, thereby further enhancing the ability of the model to extract entity relations. The experimental results reveal that, on the DialogRE data set, the DEP-GAT model performs better than the baseline model does, with an increased F1 value of 2.9% in the development set and 1.8% in the test set respectively.

中图分类号: 

  • TP391.41