基于条件随机场的事件起止时间表达式的识别

his paper breaks the traditional researches that recognize the single time expression only, it focuses on the recognition and extraction of the beginning and ending time expressions of the event in information extraction. Through the study of the previous research on the single temporal phrase recognitions, based on the capability to integrate different levels features of Conditional Random Fields(CRFs)model，this paper presents a CRFs-based approach for the beginning and ending time expressions．By analyzing a set of linguistic features of time phrases in Chinese text such as lexical features, syntactic features and context information to achieve the purpose of recognize the beginning and ending time of the event. The experimental results show a performance reaching scores of 92.1% for precision and 90.47% for recall and 88.9% for F-measure.