摘要
时间表达式识别是进行时间表达式归一化的基础,其识别结果的好坏直接影响归一化的效果。本文提出一种基于依存分析和错误驱动识别中文时间表达式的新方法。首先以时间触发词为切入点,据依存关系递归地识别时间表达式,大大地提高了识别效果;然后,采用错误驱动学习来进一步增强识别效果,根据错误识别结果和人工标注的差异自动地获取和改进规则,使系统的性能又提高了近3.5%。最终在封闭测试集和开放测试集上,F1值达到了76.38%和76.57%。
Recognizing time expressions is the foundation of its normalization, and its performance directly influences the robustness of the normalization. This paper proposes a new method for recognizing the extents of the time expressions based on dependency parsing and error-driven learning, which begins with time trigger word (namely, the syntactic head of dependency relation), uses Chinese dependency parsing to recognize the extents of the time expressions, Subsequently, we use the transformation based error-driven learning to improve the performance., which can automatically acquire and modify the rules and get 3.5 % increase after applying the learned rules. Finally, F1 = 76. 38% and F1 -76.57% results are obtained on the closed and the open test set respectively.
出处
《中文信息学报》
CSCD
北大核心
2007年第5期36-40,共5页
Journal of Chinese Information Processing
基金
国家自然科学基金资助项目(60575042)
关键词
计算机应用
中文信息处理
时间表达式识别
触发词
依存分析
错误驱动学习
computer application
Chinese information processing
time expression recognition
trigger word
dependency parsing
error-driven learning
作者简介
贺瑞芳(1979-),女,博士生,研究方向为时序信息抽取、时序文本挖掘;
秦兵(1968-),女,博士、副教授,主要研究方向为文本挖掘;
刘挺(1972-),男,博士、教授,主要研究方向为信息检索、自然语言处理。