中文事件相关性语料库构建及识别方法

J4 ›› 2015, Vol. 37 ›› Issue (12): 2306-2311.

中文事件相关性语料库构建及识别方法

黄一龙，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；2.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:2015-09-03 修回日期:2015-10-26 出版日期:2015-12-25 发布日期:2015-12-25
基金资助:
国家自然科学基金资助项目（61472265）；国家自然科学基金重点资助项目（61331011）；江苏省前瞻性联合研究资助项目（BY201405908）；软件新技术与产业化协同创新中心部分资助项目

Construction and its recognition
of Chinese relevant event

HUANG Yilong,LI Peifeng,ZHU Qiaoming

(1.School of Computer Science and Technology,Soochow University,Suzhou 215006;2.Province Key Lab of Computer Information Processing Technology of Jiangsu,Suzhou 215006,China)

Received:2015-09-03 Revised:2015-10-26 Online:2015-12-25 Published:2015-12-25

摘要/Abstract

摘要：

：事件往往围绕主题展开，相互间存在相关性。在大数据时代，从海量信息中筛选出和某个主题相关的事件，有助于信息抽取、文本摘要、文本生成等自然语言处理任务。首先提出一种相关事件的标注方法，并标注了一个中文事件相关性语料库。然后，初步提出了一个基于多种特征的相关性事件识别方法。在标注语料上的实验表明，性能在基准系统上F1值提高了408%。关键词：

关键词: 相关事件语料库, 标注, 相关性, 事件关系

Abstract:

There are many relevant events concerning a topic. In the era of big data, extracting those events which are relevant to a specific topic is helpful for many natural language processing applications, such as information extraction, text summarization, and text generation. We propose a method to annotate relevant events and construct a Chinese relevant event corpus. We then put forward a relevant event recognition approach based on various distances and semantic features. Experimental results on the annotated corpus show that the proposed approach outperforms the baseline by 4.08% in F1-measure.

Key words: relevant event corpus;annotation;relevance;event relation

黄一龙，李培峰，朱巧明. 中文事件相关性语料库构建及识别方法[J]. J4, 2015, 37(12): 2306-2311.

HUANG Yilong,LI Peifeng,ZHU Qiaoming. Construction and its recognition
of Chinese relevant event [J]. J4, 2015, 37(12): 2306-2311.

参考文献

［1］Ma Bin,Hong Yu,Yang Xuerong,et al.Using event dependency cue inference to recognize event relation ［J］.Acta Scientiarum Naturalium Universitatis Pekinensis,2013,49（1）:109116．(in Chinese)
［2］Yang Xuerong,Hong Yu,Ma Bin,et al.Event relation recognition by event term and entity inference ［J］.Journal of Chinese Information Processing,2014,28（2）:100108．(in Chinese)
［3］Zou H,Yang E,Gao Y,et al.The annotation of event schema in Chinese［C］∥Proc of the 23rd International Conference on Computational Linguistics,2010:7279．
［4］Mirza P,Sprugnoli R,Tonelli S,et al.Annotating causality in the tempeval3 corpus［C］∥Proc of the EACL 2014 Workshop on Computational Approaches to Causality in Language （CAtoCL）, 2014:1019．
［5］Chambers N,Wang S,Jurafsky D.Classifying temporal relations between events ［C］∥Proc of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, Association for Computational Linguistics,2007:173176．
［6］Chambers N, Jurafsky D. Jointly combining implicit constraints improves temporal ordering［C］∥Proc of the Conference on Empirical Methods in Natural Language Processing.Association for Computational Linguistics,2008:698706．
［7］Ittoo A,Bouma G.Extracting explicit and implicit causal relations from sparse,domainspecific texts［C］∥Proc of NLDB’11,2011:5263．
［8］Sorgente A, Vettigli G, Mele F. Automatic extraction of causeeffect relations in natural language text［C］∥DART@ AI* IA,2013,2013:3748．
［9］Wolff P.Representing causation［J］.Journal of Experimental Psychology:General,2007,136（1）:8288.
［10］Bethard S,Corvey W,Klingenstein S,et al.Building a corpus of temporalcausal structure［C］∥Proc of the 6th International Conference on Language Resources & Evaluation Lrec,2008:908915.
［11］Rink B, Bejan C A, Harabagiu S. Learning textual graph patterns to detect causal event relations［C］∥Proc of the 23rd Florida Artificial Intelligence Research Society International Conference(FLAIRS’10), Applied Natural Language Processing Track,2010:1．
［12］Zhong Zhaoman,Liu Zongtian,Zhou Wen, et al.The model of event relation representation ［J］.Journal of Chinese Information Processing,2009,23（6）:5660．(in Chinese)
附中文参考文献：
［1］马彬,洪宇,杨雪蓉,等.基于语义依存线索的事件关系识别方法研究［J］.北京大学学报(自然科学版),2013,49（1）:109116．
［2］杨雪蓉,洪宇,马彬,等.基于核心词和实体推理的事件关系识别方法［J］.中文信息学报,2014,28（2）:100108．
［12］仲兆满,刘宗田,周文,等.事件关系表示模型［J］.中文信息学报,2009,23（6）:5660．

[1]	王玉雷, 谢凯亮, 陈思贇, 胡杰, 常胜. 卷积神经网络硬件加速的通用性设计[J]. 计算机工程与科学, 2023, 45(04): 577-581.
[2]	杜洁, 骆力明, 孙众. 基于ALBERT预训练模型的事件抽取技术研究[J]. 计算机工程与科学, 2023, 45(04): 711-717.
[3]	王晨宇, 温浩珉, 郭晟楠, 林友芳, 万怀宇, . 面向快递员揽收到达时间预测的多任务深度时空网络[J]. 计算机工程与科学, 2023, 45(01): 136-144.
[4]	蔡雨岐, 郭卫斌. 基于多级语义信息融合编码的序列标注方法[J]. 计算机工程与科学, 2022, 44(12): 2266-2272.
[5]	程玉胜, 曹天成, 王一宾, 郑伟杰. 基于负相关性增强的不平衡多标签学习算法[J]. 计算机工程与科学, 2021, 43(09): 1700-1710.
[6]	魏优, 刘茂福, 胡慧君, . 基于深层语境词表示与自注意力的生物医学事件抽取[J]. 计算机工程与科学, 2020, 42(09): 1670-1679.
[7]	杨岚雁, 靳敏, 张迎春, 张珣. 一种基于关联规则的MLKNN多标签分类算法[J]. 计算机工程与科学, 2020, 42(07): 1309-1317.
[8]	王震宇1，杨辉2，杨萌杰3，魏娟1. 基于UG的采煤机防爆盖板三维标注及数控工艺研究[J]. 计算机工程与科学, 2019, 41(12): 2187-2192.
[9]	李俭兵1,2,3,刘栗材1,3. 基于改进型神经网络的影评文本情感分析算法[J]. 计算机工程与科学, 2019, 41(12): 2261-2269.
[10]	蒋芸，肖潇，侯金泉，陈莉. 基于局部正、负标记相关性的k近邻多标记分类新算法[J]. 计算机工程与科学, 2019, 41(10): 1854-1860.
[11]	蒋芸，肖潇，侯金泉，陈莉. 融合标记独有属性特征的k近邻多标记分类新算法[J]. 计算机工程与科学, 2019, 41(03): 513-519.
[12]	宋伟1,宋玉1,张帆2,范明1,叶阳东1. 基于排列熵的SAX特征表示方法复杂度及相关特性研究[J]. 计算机工程与科学, 2018, 40(07): 1303-1309.
[13]	黄进，周栋. 一种融合社会化标注系统中主题域相似的个性化排序方法[J]. 计算机工程与科学, 2018, 40(05): 880-887.
[14]	秦铭，蔡明. 基于分类融合和关联规则挖掘的图像语义标注[J]. 计算机工程与科学, 2018, 40(05): 950-956.
[15]	邱亮1，夏慧明1，储久良2. 基于时域梯度相似度的视频质量评价模型[J]. 计算机工程与科学, 2018, 40(04): 707-711.