计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 52-56.doi: 10.11896/jsjkx.201200259

• 智能计算 • 上一篇    下一篇

基于门控图卷积与动态依存池化的事件论元抽取

王士浩, 王中卿, 李寿山, 周国栋   

  1. 苏州大学计算机科学与技术学院 江苏 苏州215006
  • 出版日期:2021-11-10 发布日期:2021-11-12
  • 通讯作者: 王中卿(wangzq@suda.edu.cn)
  • 作者简介:shwang10@stu.suda.edu.cn
  • 基金资助:
    国家自然科学基金青年科学基金项目(61806137)

Event Argument Extraction Using Gated Graph Convolution and Dynamic Dependency Pooling

WANG Shi-hao, WANG Zhong-qing, LI Shou-shan, ZHOU Guo-dong   

  1. School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:WANG Shi-hao,born in 1997,postgra-duate,is a member of China Computer Federation.His main research interests include natural language processing and so on.
    WANG Zhong-qing,born in 1987,Ph.D,associate professor.His main research interests include natural language processing and so on.
  • Supported by:
    Young Scientists Fund of the National Natural Science Foundation of China(61806137).

摘要: 事件论元抽取是事件抽取任务中一个极具挑战性的子任务。该任务旨在抽取事件中的论元及论元扮演的角色。研究发现,句子的语义特征和依存句法特征对事件论元抽取都有着非常重要的作用,现有的方法往往未考虑如何将两种特征有效地融合起来。因此,提出一种基于门控图卷积与动态依存池化的事件论元抽取模型。该方法使用BERT抽取出句子的语义特征;然后通过依存句法树设计两个相同的图卷积网络,抽取句子的依存句法特征,其中一个图卷积的输出会通过激活函数作为门控单元;接着,语义特征和依存句法特征通过门控单元后相加融合。此外,还设计了一个动态依存池化层对融合后的特征进行池化。在ACE2005数据集上的实验结果表明,该模型可以有效地提升事件论元抽取效果。

关键词: 门控机制, 事件论元抽取, 图卷积, 依存句法特征, 语义特征

Abstract: Event argument extraction is a very challenging subtask of event extraction.This task aims to extract the arguments in the event and the role they played.It is found that the semantic features and dependency features of sentences play a very important role in event argument extraction,and the existing methods often don't consider how to integrate them effectively.Therefore,this paper proposes an event argument extraction model using gated graph convolution and dynamic dependency pooling.This method uses BERT to extract the semantic features of sentences,and then two same graph convolution networks are used to extract the dependency features of sentences based on the dependency tree.The output of one graph convolution is used as the gating unit through the activation function.Then semantic features and dependency features are added and fused through gate unit.In addition,a dynamic dependency pooling layer is designed to pool the fused features.The experiment results on ACE2005 dataset show that the proposed model can effectively improve the performance of event argument extraction.

Key words: Dependency features, Event argument extraction, Gate mechanism, Graph convolution, Semantic features

中图分类号: 

  • TP391
[1]DEVLIN J,CHANG M W,LEE K,et al.Bert:pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of NAACL-HLT.2019:4171-4186.
[2]KIPF T N,WELLING M.Semi-Supervised Classification withGraph Convolutional Networks[C]//Proceedings of ICLR.2017.
[3]SU J L.Reading comprehension question answering model based on CNN:DGCNN [EB/OL](2018-07-28).https://spaces.ac.cn/archives/-5409.
[4]DAVID A.The stages of event extraction[C]//Proceedings of the Workshop on Annotating and Reasoning about Time and Events.2006:1-8.
[5]LIAO S,GRISHMAN R.Using document level cross-event inference to improve event extraction[C]//Proceedings of ACL.2010:789-797.
[6]HONG Y,ZHANG J F,MA B,et al.Using cross-entity infer-ence to improve event extraction[C]//Proceedings of ACL-HLT.2011:1127-1136.
[7]MCCLOSKY D,SURDEANU M,CHRISTOPHER D M.Event extraction as dependency parsing[C]//Proceedings of ACL-HLT.2011:1626-1635.
[8]LI Q,JI H,HUANG L.Joint event extraction via structuredprediction with global features[C]//Proceedings of ACL.2013:73-82.
[9]LI P,ZHU Q,ZHOU G.Joint modeling of argument identification and role determination in Chinese event extraction with discourse-level information[C]//Proceedings of IJCAI.2013.
[10]CHEN Y B,XU L H,LIU K,et al.Event extraction via dynamic multi-pooling convolutional neural networks[C]//Proceedings of ACL.2015:409-419.
[11]NGUYEN T H,CHO K,GRISHMAN R.Joint event extraction via recurrent neural networks[C]//Proceedings of NAACL-HLT.2016:300-309.
[12]WANG X Z,WANG Z Q,HAN X,et al.HMEAE:Hierarchical Modular Event Argument Extraction[C]//Proceedings of EMNLP.2019:5781-5787.
[13]NGUYEN T,GRISHMAN R.Graph convolutional networkswith argument-aware pooling for event detection[C]//Proceedings of AAAI.2018:5900-5907.
[14]YAN H,JIN X L,MEMG X B,et al.Event Detection with Multi-Order Graph Convolution and Aggregated Attention[C]//Proceedings of EMNLP.2019:5766-5770.
[15]LIU X,ZHUNCHEN L,HEYAN H.Jointly multiple events extraction via attentionbased graph information aggregation[C]//Proceedings of EMNLP.2018:1247-1256.
[16]SHA L,QIAN F,CHANG B B,et al.Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction[C]//Proceedings of AAAI.2018:5916-5923.
[17]KINGM D,BA J.Adam:A Method for Stochastic Optimization[C]//Proceedings of ICLR.2015.
[18]SHA L,LIU J,LIN C Y,et al.RBPB:Regularization-based pattern balancing method for event extraction[C]//Proceedings of ACL.2016:1224-1234.
[1] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[2] 汪鸣, 彭舰, 黄飞虎.
基于多时间尺度时空图网络的交通流量预测模型
Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction
计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[3] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[4] 李健智, 王红玲, 王中卿.
基于图卷积网络的专利摘要自动生成研究
Automatic Generation of Patent Summarization Based on Graph Convolution Network
计算机科学, 2022, 49(6A): 172-177. https://doi.org/10.11896/jsjkx.210400117
[5] 邵延华, 李文峰, 张晓强, 楚红雨, 饶云波, 陈璐.
基于时空图卷积和注意力模型的航拍暴力行为识别
Aerial Violence Recognition Based on Spatial-Temporal Graph Convolutional Networks and Attention Model
计算机科学, 2022, 49(6): 254-261. https://doi.org/10.11896/jsjkx.210400272
[6] 赵小虎, 叶圣, 李晓.
多算法融合的骨骼重建信息动作分类方法
Multi-algorithm Fusion Behavior Classification Method for Body Bone Information Reconstruction
计算机科学, 2022, 49(6): 269-275. https://doi.org/10.11896/jsjkx.210500070
[7] 李子仪, 周夏冰, 王中卿, 张民.
基于用户关联的立场检测
Stance Detection Based on User Connection
计算机科学, 2022, 49(5): 221-226. https://doi.org/10.11896/jsjkx.210400135
[8] 高越, 傅湘玲, 欧阳天雄, 陈松龄, 闫晨巍.
基于时空自适应图卷积神经网络的脑电信号情绪识别
EEG Emotion Recognition Based on Spatiotemporal Self-Adaptive Graph ConvolutionalNeural Network
计算机科学, 2022, 49(4): 30-36. https://doi.org/10.11896/jsjkx.210900200
[9] 周海榆, 张道强.
面向多中心数据的超图卷积神经网络及应用
Multi-site Hyper-graph Convolutional Neural Networks and Application
计算机科学, 2022, 49(3): 129-133. https://doi.org/10.11896/jsjkx.201100152
[10] 李浩, 张兰, 杨兵, 杨海潇, 寇勇奇, 王飞, 康雁.
融合双重权重机制和图卷积神经网络的微博细粒度情感分类
Fine-grained Sentiment Classification of Chinese Microblogs Combining Dual Weight Mechanismand Graph Convolutional Neural Network
计算机科学, 2022, 49(3): 246-254. https://doi.org/10.11896/jsjkx.201200073
[11] 邓维斌, 朱坤, 李云波, 胡峰.
FMNN:融合多神经网络的文本分类模型
FMNN:Text Classification Model Fused with Multiple Neural Networks
计算机科学, 2022, 49(3): 281-287. https://doi.org/10.11896/jsjkx.210200090
[12] 潘志豪, 曾碧, 廖文雄, 魏鹏飞, 文松.
基于交互注意力图卷积网络的方面情感分类
Interactive Attention Graph Convolutional Networks for Aspect-based Sentiment Classification
计算机科学, 2022, 49(3): 294-300. https://doi.org/10.11896/jsjkx.210100180
[13] 申浩希, 牛保宁.
半虚拟化框架Virtio下的实时网络I/O请求门控机制
Gating Mechanism for Real-time Network I/O Requests Based on Para-virtualization Virtio Framework
计算机科学, 2022, 49(2): 368-376. https://doi.org/10.11896/jsjkx.210100110
[14] 解宇, 杨瑞玲, 刘公绪, 李德玉, 王文剑.
基于动态拓扑图的人体骨架动作识别算法
Human Skeleton Action Recognition Algorithm Based on Dynamic Topological Graph
计算机科学, 2022, 49(2): 62-68. https://doi.org/10.11896/jsjkx.210900059
[15] 苗启广, 辛文天, 刘如意, 谢琨, 王泉, 杨宗凯.
面向智慧教育行为分析的图卷积骨架动作识别方法
Graph Convolutional Skeleton-based Action Recognition Method for Intelligent Behavior Analysis
计算机科学, 2022, 49(2): 156-161. https://doi.org/10.11896/jsjkx.220100061
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!