【作者】 孟雷； 丁效； 秦兵； 刘挺；

【Author】 Meng Lei,Ding Xiao,Qin Bing,Liu Ting Information Retrieval Laboratory of Computer Science & Technology School,Harbin Institute of Technology,Harbin 150001

【机构】 哈尔滨工业大学计算机学院信息检索研究室；

【摘要】 事件抽取是信息抽取领域一个重要的研究方向。针对金融领域特定事件的事件元素抽取,本文提出了基于依存句法分析的事件元素核心词抽取方法,并结合短语结构句法分析进行事件元素完整边界的识别。实验表明,依存句法结合规则可以有效地抽取事件元素核心词,再结合短语结构句法则可以比较准确的识别出完整的事件元素。更多还原

【Abstract】 Event extraction is an important research area in information extraction field.Aiming to extracting the event arguments of particular event in financial field,this paper presents the extraction method of the event argument’s key word based on dependency parsing;and we have also applied the Noun Phrase parsing to the recognition of the noun phrase where the event argument locates.The experiment shows that the dependency parsing and the rules could efficiently extract the key word of the event argument,and the Noun Phrase parsing could accurately recognize the whole event argument更多还原