基于时间关系的Bi-LSTM+GCN因果关系抽取

吉林大学学报(理学版) ›› 2021, Vol. 59 ›› Issue (3): 643-648.

基于时间关系的Bi-LSTM+GCN因果关系抽取

郑余祥¹, 左祥麟^1,2, 左万利^1,2, 梁世宁¹, 王英^1,2

1. 吉林大学计算机科学与技术学院, 长春 130012; 2. 吉林大学符号计算与知识工程教育部重点实验室, 长春 130012

收稿日期:2020-06-01 出版日期:2021-05-26 发布日期:2021-05-23
通讯作者: 左祥麟 E-mail:zxl_jlu@163.com

Bi-LSTM+GCN Causality Extraction Based on Time Relationship

ZHENG Yuxiang¹, ZUO Xianglin^1,2, ZUO Wanli^1,2, LIANG Shining¹, WANG Ying^1,2

1. College of Computer Science and Technology, Jilin University, Changchun 130012, China;
2. Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China

Received:2020-06-01 Online:2021-05-26 Published:2021-05-23

摘要/Abstract

摘要： 针对传统时间关系只应用在机器学习方向关系抽取的问题, 提出一种基于序列标注实体识别的关系抽取方法. 先构建双向长短期记忆网络(Bi-LSTM)模型进行特征提取, 再输入时间关系作为特征矩阵进行图卷积. 实验结果表明: 时间关系能提高因果关系抽取效果, 并且包含时间关系的Bi-LSTM+GCN模型能有效抽取因果事件; 带有时间关系的Bi-LSTM+GCN模型获得因果关系的抽取结果优于传统方法因果关系的抽取结果.

关键词: 因果关系抽取, 时间关系, 序列标注, 图卷积, 双向长短期记忆网络(Bi-LSTM)

Abstract: Aiming at the problem that traditional time relationships were only applied in the direction of machine learning, we proposed a relationship extraction method based on sequence labeling entity recognition. We first constructed Bi-LSTM model for feature extraction, and then input time relationship as a characteristic matrix for graph convolution. The experimental results show that the time relationship can improve the effect of causality extraction, and the Bi-LSTM+GCN model containing time relationship can effectively extract causal events, and the results of causality extraction of the Bi-LSTM+GCN model with time relationship are better than those of traditional methods.

Key words: causality extraction, time relationship, sequence labeling, graph convolution, bidirectional long short-term memory (Bi-LSTM)

中图分类号:

TP391

郑余祥, 左祥麟, 左万利, 梁世宁, 王英. 基于时间关系的Bi-LSTM+GCN因果关系抽取[J]. 吉林大学学报(理学版), 2021, 59(3): 643-648.

ZHENG Yuxiang, ZUO Xianglin, ZUO Wanli, LIANG Shining, WANG Ying. Bi-LSTM+GCN Causality Extraction Based on Time Relationship[J]. Journal of Jilin University Science Edition, 2021, 59(3): 643-648.

[1]	杨妮亚, 赵维, 潘石, 吕桂新. 基于数据增强的域自适应图卷积网络[J]. 吉林大学学报(理学版), 2026, 64(2): 311-0318.
[2]	李岳泽, 左祥麟, 左万利, 梁世宁, 张一嘉, 朱媛. 基于BERT-GCN的因果关系抽取[J]. 吉林大学学报(理学版), 2023, 61(2): 325-330.
[3]	姜博, 左万利, 王英. 基于BERT的因果关系抽取[J]. 吉林大学学报(理学版), 2021, 59(6): 1439-1444.