计算机科学 ›› 2021, Vol. 48 ›› Issue (4): 249-253.doi: 10.11896/jsjkx.200300156

• 人工智能 • 上一篇    下一篇

基于字词联合表示的中文事件检测方法

吴凡, 朱培培, 王中卿, 李培峰, 朱巧明   

  1. 苏州大学计算机科学与技术学院 江苏 苏州215006
  • 收稿日期:2020-06-24 出版日期:2021-04-15 发布日期:2021-04-09
  • 通讯作者: 朱巧明(qmzhu@suda.edu.cn)
  • 基金资助:
    国家自然科学基金项目(61836007,61806137,61772354);江苏省高等学校自然科学研究面上项目(18KJB520043)

Chinese Event Detection with Joint Representation of Characters and Words

WU Fan, ZHU Pei-pei, WANG Zhong-qing, LI Pei-feng, ZHU Qiao-ming   

  1. School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China
  • Received:2020-06-24 Online:2021-04-15 Published:2021-04-09
  • About author:WU Fan,born in 1996,postgraduate.His main research interests include natu-ral language processing and so on.(944721805@qq.com)
    ZHU Qiao-ming,born in 1963,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.His main research interests include natural language processing and so on.
  • Supported by:
    National Natural Science Foundation of China(61836007,61806137,61772354) and Natural Science Foundation of Jiangsu Province(18KJB520043).

摘要: 事件检测作为事件抽取的一个子任务,是当前信息抽取的研究热点之一。它在构建知识图谱、问答系统的意图识别和阅读理解等应用中有着重要的作用。与英文字母不同,中文中的字在很多场合作为单字词具有特定的语义信息,且中文词语内部也存在特定的结构形式。根据中文的这一特点,文中提出了一种基于字词联合表示的图卷积模型JRCW-GCN(Joint Representation of Characters and Words by Graph Convolution Neural Network),用于中文事件检测。JRCW-GCN首先通过最新的BERT预训练语言模型以及Transformer模型分别编码字和词的语义信息,然后利用词和字之间的关系构建对应的边,最后使用图卷积模型同时融合字词级别的语义信息进行事件句中触发词的检测。在ACE2005中文语料库上的实验结果表明,JRCW-GCN的性能明显优于目前性能最好的基准模型。

关键词: 联合表示, 图卷积, 中文事件检测

Abstract: As a sub-task of event extraction,event detection is a research hotspot in information extraction.It plays an important role in many NLP applications,such as knowledge graph,question answering and reading comprehension.Different with English character,a Chinese character can be regarded as single-character word and has its certain meaning.Moreover,there are specific structures in Chinese words.Therefore,this paper proposes a Chinese event detection model based on graph convolution neural network,called JRCW-GCN(Joint Representation of Characters and Words by Graph Convolution Neural Network),which integrates Chinese character and word representation.It uses the latest BERT and Transformer to encode the semantic information of words and characters respectively,and then uses the relationship between words and characters to construct the corresponding edges.Finally,it uses the graph convolution model to detect Chinese events by integrating the semantic information in Chinese character and word level.The experimental results on the ACE2005 Chinese corpus show that the performance of our model outperforms the state-of-the-art models.

Key words: Chinese event detection, Graph convolution, Joint representation

中图分类号: 

  • TP391
[1]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.<br /> [2]LI P,ZHU Q,DIAO H,et al.Joint modeling of trigger identification and event type determination in Chinese event extraction[C]//Proceedings of COLING 2012.2012:1635-1652.<br /> [3]LI P,ZHOU G,ZHU Q,et al.Employing compositional semantics and discourse consistency in Chinese event extraction[C]//Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.2012:1006-1016.<br /> [4]CHEN C,NG V.Joint modeling for chinese event extractionwith rich linguistic features[C]//Proceedings of COLING 2012.2012:529-544.<br /> [5]GRISHMAN R,WESTBROOK D,MEYERS A.Nyu’s english ace 2005 system description[J].ACE,2005,5.<br /> [6]JI H,GRISHMAN R.Refining event extraction through cross-document inference[C]//Proceedings of ACL-08:HLT.2008:254-262.<br /> [7]LIAO S,GRISHMAN R.Using document level cross-event inference to improve event extraction[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2010:789-797.<br /> [8]HONG Y,ZHANG J,MA B,et al.Using cross-entity inference to improve event extraction[C]//Proceedings of the 49thAnnualMeeting of the Association for Computational Linguistics:Human Language Technologies.Association for Computational Linguistics,2011:1127-1136.<br /> [9]COLLOBERT R,WESTON J,BOTTOU L,et al.Natural language processing(almost) from scratch[J].Journal of Machine Learning Research,2011,12(Aug):2493-2537.<br /> [10]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.<br /> [11]CHO K,VAN MERRIËNBOER B,GULCEHRE C,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].arXiv:1406.1078,2014.<br /> [12]LIU S,CHEN Y,LIU K,et al.Exploiting argument information to improve event detection via supervised attention mechanisms[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:1789-1798.<br /> [13]LIU S,CHEN Y,HE S,et al.Leveraging framenet to improve automatic event detection[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.2016:2134-2143.<br /> [14]LIU J,CHEN Y,LIU K,et al.Event detection via gated multilingual attention mechanism[C]//Thirty-Second AAAI Confe-rence on Artificial Intelligence.2018.<br /> [15]NGUYEN T H,GRISHMAN R.Graph convolutional networks with argument-aware pooling for event detection[C]//Thirty-Second AAAI Conference on Artificial Intelligence.2018.<br /> [16]ZENG Y,YANG H,FENG Y,et al.A convolution BiLSTM neural network model for Chinese event extraction[M]//Natural Language Understanding and Intelligent Applications.Springer,Cham,2016:275-287.<br /> [17]LIN H,LU Y,HAN X,et al.Nugget Proposal Networks forChinese Event Detection[J].arXiv:1805.00249,2018.<br /> [18]DING N,LI Z,LIU Z,et al.Event Detection with Trigger-Aware Lattice Neural Network[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Proces-sing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:347-356.<br /> [19]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is All you Need[C]//Neural Information Processing Systems.2017:5998-6008.<br /> [20]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[J].arXiv:1810.04805,2018.<br /> [21]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.<br /> [22]LI S,ZHAO Z,HU R,et al.Analogical reasoning on chinese morphological and semantic relations[J].arXiv:1805.06504,2018.<br /> [23] FENG X,QIN B,LIU T.A language-independent neural network for event detection[J].Science China Information Sciences,2018,61(9):092106.
[1] 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
[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] 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
[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] 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
[12] 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
[13] 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
[14] 张虎, 柏萍.
融入句子中远距离词语依赖的图卷积短文本分类方法
Graph Convolutional Networks with Long-distance Words Dependency in Sentences for Short Text Classification
计算机科学, 2022, 49(2): 279-284. https://doi.org/10.11896/jsjkx.201200062
[15] 干创, 吴桂兴, 詹庆原, 王鹏焜, 彭志磊.
基于骨架模态的多级门控图卷积动作识别网络
Multi-scale Gated Graph Convolutional Network for Skeleton-based Action Recognition
计算机科学, 2022, 49(1): 181-186. https://doi.org/10.11896/jsjkx.201100164
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!