领域事件图谱构建方法综述  

Domain-Specific Event Graph Construction Methods:A Review

作　　者：王毅[1] 沈喆 姚毅凡 成颖[1,2] Wang Yi;Shen Zhe;Yao Yifan;Cheng Ying(School of Information Management,Nanjing University,Nanjing 210023,China;School of Chinese Language and Literature,Shandong Normal University,Jinan 250014,China)

机构地区：[1]南京大学信息管理学院,南京210023 [2]山东师范大学文学院,济南250014

出　　处：《数据分析与知识发现》2020年第10期1-13,共13页Data Analysis and Knowledge Discovery

基　　金：国家社会科学基金重大项目“中国近现代文学期刊全文数据库建设与研究(1872-1949)”(项目编号:17ZDA276)的研究成果之一。

摘　　要：【目的】分析并评述领域事件知识图谱构建的相关研究,为后续研究提供理论基础和实践指导。【文献范围】利用Web of Science核心数据库和Google Scholar以"Event Graph"、"Event extraction"和"Event relation"等主题词进行检索,经过手工筛选获得代表性文献61篇。【方法】采用文献调研方法系统梳理领域事件图谱在定义、构建流程、识别方法等方面的工作。总结了基于规则、基于特征学习以及基于神经网络三种事件抽取的方法,对事件抽取与事件关系抽取中的特征选择、模型架构以及实验结果等进行分析和对比。【结果】借鉴通用图谱构建的方法,提出包括事件触发词识别、事件要素识别、事件关系识别以及事件存储等在内的领域事件图谱构建流程模型。从描述结构、领域限制、事件形式、推理能力和时序关系等角度阐明构建标准应具备的元素。在构建实践中,事件本体的借鉴和复用是必要选项,事件抽取采用神经网络方法是目前最优的选择。【局限】由于标准数据集的缺失,事件关系抽取对比中未能采用统一的数据集进行量化比较。【结论】提出从知识提升、迁移学习以及认知模型等三个视角开展该主题后继研究的建议。[Objective] This paper reviews construction methods for domain-specific event graphs, aiming to facilitate future research. [Coverage] We searched"Event Graph","Event extraction"and"Event relation"with Web of Science and Google Scholar, then retrieved a total of 61 representative literature. [Methods] We summarized the definition, construction process and extraction methods with literature review. Then, we discussed the rule-based, feature learning based, and neural network-based extraction techniques. Finally, we analyzed their feature selection procedures, model architecture and experiment results. [Results] Refer to the general knowledge graph construction methods, we proposed a process model that include trigger argument and relation recognition. We briefly described on construction standard in structure, domain, event form, inference ability and temporal relations. In practice, we found that Ontology reuse is necessary, and neural network is the best choice. [Limitations] We did not use the same dataset to evaluate all methods. [Conclusions] We proposed knowledge-boosted methods, transfer learning and cognitive models for future studies.

关 键 词：领域事件图谱 知识图谱 事件抽取 信息提取 

分 类 号：G350[文化科学—情报学]