摘要
文本信息抽取是处理海量文本数据的手段,事件信息抽取是其中最具挑战性的任务之一。提出了一种基于条件随机场的语义角色标注方法,该方法以浅层句法分析为基础,把短语或命名实体作为标注的基本单元,将条件随机场用于句子中谓词的语义角色标注。应用该方法对"职务变动"和"会见"两类事件的事件要素及其语义角色进行标注,在各自的测试集上分别获得了77.3%和74.2%的综合指标F值。
Text information extraction is an important means of processing large quantity of text. Event extraction is one of the most challenge tasks of the research on information extraction. A method based on conditional random fields （CRFs） is proposed for Semantic Role Labeling （SRL）. This method takes shallow syntactic parsing as base, and takes phrase or named entity as the labeled units, and CRFs model is trained to label the predicates＇ semantic roles in a sentence. The method is used to label event argument and its roles on two test sets of management succession and meeting, and the F measure is 77.3% and 74.2% respectively.
出处
《计算机科学》
CSCD
北大核心
2008年第3期155-157,共3页
Computer Science
基金
教育部博士点基金项目(20050007023)
关键词
语义角色标注
条件随机场
事件信息抽取
事件要素
Semantic role labeling, Conditional random fields, Event information extraction, Event argument
