计算机科学 ›› 2019, Vol. 46 ›› Issue (8): 277-281.doi: 10.11896/j.issn.1002-137X.2019.08.046

• 人工智能 • 上一篇    下一篇

基于多注意力机制的事件同指消解方法

方杰, 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)
    (江苏省计算机信息处理技术重点实验室 江苏 苏州215006)
  • 收稿日期:2018-07-29 出版日期:2019-08-15 发布日期:2019-08-15
  • 通讯作者: 李培峰(1971-),男,教授,博士生导师,主要研究领域为自然语言处理和机器学习,E-mail:pfli@suda.edu.cn
  • 作者简介:方杰(1993-),男,硕士生,主要研究领域为中文信息处理;朱巧明(1963-),男,教授,博士生导师,主要研究领域为中文信息处理
  • 基金资助:
    国家自然科学基金(61472265,61772354,61773276)

Employing Multi-attention Mechanism to Resolve Event Coreference

FANG Jie, LI Pei-feng, ZHU Qiao-ming   

  1. (School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China)
    (Province Key Laboratory of Computer Information Processing Technology of Jiangsu,Suzhou,Jiangsu 215006,China)
  • Received:2018-07-29 Online:2019-08-15 Published:2019-08-15

摘要: 事件同指消解是信息抽取的一项重要任务,在信息融合、问答系统、阅读理解中都有着重要的作用。文中提出了一种基于多种注意力机制的卷积神经网络的CorefNet方法,用于消解文档级事件同指。该方法通过深层卷积网络抽取事件特征,并使用多种注意力机制获取重要信息。相比过去大部分建立在概率模型和图模型上的传统方法,所提方法仅使用了少量特征;与目前主流的神经网络模型相比,文中方法可以提取深层的事件特征,明显提高了事件同指消解的准确率。在ACE2005数据集上的实验验证了CorefNet优于目前最优的基准系统。

关键词: 深层卷积网络, 事件同指, 文档级, 注意力机制

Abstract: Event coreference resolution is an asignificant subtask of information extraction and plays an import role in information fusion,QA system and reading comprehension.This paper introduced a multi-attention-based CNN neural network,called CorefNet,to resolve document-level event coreference.CorefNet uses a deep CNN to extract event features and a multi-attention mechanism to capture important features.Compared with most previous studies with probability-based or graph-based models,the proposed model only uses a few features.Compared with the current main stream nueral network model,this menthod can extract deep event features,and significantly improve the performance of event coreference resolution.The experimental results on the ACE2005 corpus show that this model achieves the state-of-the-art results

Key words: Attention mechanism, Deep CNN, Document-level, Event coreference

中图分类号: 

  • TP391
[1]ALLAN J,CARBONELL J G,DODDINGTON G,et al.Topic Detection and Tracking Pilot Study:Final report[C]∥Procee-dings of the DARPA Broadcast News Transcription and Understanding Workshop.Burlington:Morgan Kaufmann Press,1998:194-218.
[2]LI P F,ZHU Q M,ZHOU G D.Argument Inference from Relevant Event Mentions in Chinese Argument Extraction[C]∥Proceedings of ACL 2013.Minneapolis:ACL Press,2013:1477-1487.
[3]NARAYANAN S,HARABAGIU S.Question Answering Based on Semantic Structures[C]∥Proceedings of COLING 2004.Switzerland:ACL Press,2004:693-702.
[4]CHOUBEY P K,HUANG R H.Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events[C]∥Proceedings of EMNLP 2017.Copenhagen:ACL Press,2017:2124-2133.
[5]CHEN Z,JI H.Graph-based Event Coreference Resolution [C]∥Proceedings of TextGraphs 4.Singapore:ACL Press,2009:54-57.
[6]HAGHIGHI A,KLEIN D.Simple Coreference Resolution with Rich Syntactic and Semantic Features[C]∥Proceedings of EMNLP 2009.Singapore:ACL Press,2009:1152-1161.
[7]NG V,CARDIE C.Identifying Anaphoric and Non-Anaphoric Noun Phrases to Improve Coreference Resolution[C]∥Procee-dings of COLING 2002.Taipei:ACL Press,2002:1-7.
[8]CHEN Z,JI H,HARALICK R.A Pairwise Event Coreference Model,Feature Impact and Evaluation for Event Coreference Resolution[C]∥Proceedings of the Workshop on Events in Emerging Text Types.Borovets:ACL Press,2009:17-22.
[9]LIU Z Z,ARAKI J,HOVY E,et al.Supervised Within-Docu- ment Event CoReference Using Information Propagation[C]∥Proceedings of LREC 2014.Reykjavik:Springer,2014:4539-4544.
[10]LU J,NG V.Joint Learning for Event Coreference Resolution[C]∥Proceedings of ACL 2017.Vancouver:ACL Press,2017:90-101.
[11]KIM Y.Convolutional Neural Networks for Sentence Classification[C]∥Proceedings of EMNLP 2014.Doha:ACL Press,2014:1746-1751.
[12]YIH W T,TOUTANOVA K,PLATT J C,et al.Learning Discriminative Projections for Text Similarity Measures[C]∥Proceedings of CoNLL 2011.Oregan:ACL Press,2011:247-256.
[13]KRAUSE S,XU F Y,USZKOREIT H,et al.Event Linking with Sentential Features from Convolutional Neural Networks[C]∥Proceedings of CoNLL 2016.Berlin:ACL Press,2016:239-249.
[14]VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[C]∥Proceedings of NLPS 2017.California:MIT Press,2017:5998-6008.
[15]PENNINGTON J,SOCHER R,MANNING C,et al.Glove: Global Vectors for Word Representation[C]∥Proceedings of EMNLP 2014.Doha:ACL Press,2014:1532-1543.
[16]BAGGA A,BALDWIN B.Algorithms for Scoring Coreference Chains[C]∥Proceedings of LREC 1998.Granada:ELRA Press,1998:563-566.
[17]LUO X Q.On Coreference Resolution Performance Metrics [C]∥Proceedings of EMNLP 2005.Vancouver:ACL Press,2005:25-32.
[18]VILAIN M,BURGER J,ABERDEEN J,et al.A Model-Theoretic Coreference Scoring Scheme[C]∥Proceedings of MUC-6.California:ACM Press,1998:45-52.
[1] 周芳泉, 成卫青.
基于全局增强图神经网络的序列推荐
Sequence Recommendation Based on Global Enhanced Graph Neural Network
计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2] 戴禹, 许林峰.
基于文本行匹配的跨图文本阅读方法
Cross-image Text Reading Method Based on Text Line Matching
计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[3] 周乐员, 张剑华, 袁甜甜, 陈胜勇.
多层注意力机制融合的序列到序列中国连续手语识别和翻译
Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion
计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[4] 熊丽琴, 曹雷, 赖俊, 陈希亮.
基于值分解的多智能体深度强化学习综述
Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization
计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[5] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[6] 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
[7] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[8] 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥.
基于注意力机制的医学影像深度哈希检索算法
Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism
计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[9] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[10] 闫佳丹, 贾彩燕.
基于双图神经网络信息融合的文本分类方法
Text Classification Method Based on Information Fusion of Dual-graph Neural Network
计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[11] 张颖涛, 张杰, 张睿, 张文强.
全局信息引导的真实图像风格迁移
Photorealistic Style Transfer Guided by Global Information
计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[12] 曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨.
基于注意力机制的细粒度语义关联视频-文本跨模态实体分辨
Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism
计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224
[13] 徐鸣珂, 张帆.
Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法
Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition
计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085
[14] 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强.
基于向量注意力机制GoogLeNet-GMP的行人重识别方法
Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism
计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198
[15] 金方焱, 王秀利.
融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取
Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM
计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!