摘要
该文针对中文阅读理解问答中的时间、人物、地点、数值、实体、描述六类问题,制定了各类问题回答的启发式规则集。对规则集中每条规则赋予一个相应权值,利用正交表对各规则所对应的权值进行了调优选取,给出了各候选答案句基于相应规则的得分计算方法。该文方法在山西大学自主开发的中文阅读理解语料库CRCC v1.1上进行了实验,在整个语料库上得到了83.09%的HumSent准确率。为了与文献[10]中的最大熵方法比较,该文在与文献[10]中完全相同的训练集上调优规则的权值,在相同的测试集上测试,最终得到HumSent准确率81.13%,比最大熵的方法高大约1%,且在全部的六类问题上,该文方法的HumSent准确率都不低于最大熵方法。
This paper constructs a set of heuristic rules for six types of question regarding to time, human, location, number, entity and description in Chinese QARC system. Each rule is further assigned with a weight optimized by the orthogonal array. Then the calculation of each candidate answer sentence is described over corresponding rules. The experiment on the CRCC v1. 1 （Chinese reading comprehension corpus） built by Shanxi University produces 83.09% HumSent accuracy. Compare with the results of ME-based method, the proposed approach achieves 81.13% HumSent accuracy, which is about 1% higher than the ME-based results on the same training and testing environment.
出处
《中文信息学报》
CSCD
北大核心
2009年第4期3-9,共7页
Journal of Chinese Information Processing
基金
国家自然科学基金资助项目(60873128)
国家社会科学基金青年资助项目(07CYY022)
关键词
计算机应用
中文信息处理
阅读理解
问答系统
规则
正交表
computer application
Chinese information processing
reading comprehension
question answering
heuristic rules
orthogonal array
