汉语表述识别与指代消解  

Expression Recognition and Anaphora Resolution in Chinese

作　　者：黄学华[1] 孔芳[1,2] 周国栋[1,2] 

机构地区：[1]苏州大学计算机科学与技术学院自然语言处理实验室,江苏苏州215006 [2]苏州大学江苏省计算机信息处理技术重点实验室,江苏苏州215006

出　　处：《计算机工程》2016年第9期168-173,共6页Computer Engineering

基　　金：国家自然科学基金资助项目(61333018;61472264)

摘　　要：使用传统的机器学习方法构建汉语指代消解基准平台,当引入表述识别二次分类器后,基准平台的性能并没有获得提升。针对该问题,提出一种改进的表述识别方法。改进的表述识别方法只针对代词、专有名词进行分类过滤,而对所有的普通名词短语予以保留。实验结果表明,与传统基于规则的表述识别方法相比,改进方法可以有效提升全自动的汉语指代消解性能。Using the traditional machine learning method,an Chinese coreference resolution standard platform is built. After the introduction of quadratic expression recognition classifier, the performance of the standard platform is not promoted. Aiming at this problem, an improved expression recognition method is proposed. The method only classifies person pronoun and proper noun, and all common noun phrases are maintained, Experimental results show that the improved method can effectively improve the performance of automatic anaphora resolution in Chinese compared with traditional rule-based expression recognition method.

关 键 词：指代消解 表述识别 机器学习 句法分析 语料 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]