CAJ | 학술논문

以现代哈萨克语短语识别与短语块库构建技术研究工程为背景，以NP和VP结构的歧义类型研究及消除为目的，提取统计方法来处理NP和VP结构的歧义问题．该方法在已经统计与分析出的哈萨克语短语基础上，对哈萨克语NP和VP短语组合结构歧义做全面分析和整理．用互信息方法解决NP和VP的歧义问题准确率（72％）并不高．为了达到更好的准确率就需要数量较大的训练语料库，但是目前实验环境并没有足够的语料．因此，基于规则方法标注好语料并采用人工方式完善训练语料库，再使用最大熵方法来处理歧义问题．实验结果表明，基于统计方法解决N P和V P结构的歧义问题是有效的，其准确率在封闭测试中达到了80.1％．
이현대합살극어단어식별여단어괴고구건기술연구공정위배경，이NP화VP결구적기의류형연구급소제위목적，제취통계방법래처리NP화VP결구적기의문제．해방법재이경통계여분석출적합살극어단어기출상，대합살극어NP화VP단어조합결구기의주전면분석화정리．용호신식방법해결NP화VP적기의문제준학솔（72％）병불고．위료체도경호적준학솔취수요수량교대적훈련어료고，단시목전실험배경병몰유족구적어료．인차，기우규칙방법표주호어료병채용인공방식완선훈련어료고，재사용최대적방법래처리기의문제．실험결과표명，기우통계방법해결N P화V P결구적기의문제시유효적，기준학솔재봉폐측시중체도료80.1％．
This paper aims to building modern Kazakh phrase recognition chunk library in technology re-search ,and use statistical methods to solve the problem that NP and VP ambiguous structure the ambigui-ty .In this method statistics and Analysis Kazakh phrase structure knowledge ,and analysis the Kazakh NP and VP phrase combination of structural ambiguity in more comprehensive system .The study has ap-plied mutual information processing NP VP of ambiguity ,but this algorithm is the accuracy rate is not high only 72% .To achieve better accuracy need a large number of training corpus in order ,but the experi-mental environment and do not have enough corpus .Therefore ,based on a small number of rule-based method marked corpus and added artificially to improve the training corpus ,and then in the maximum en-tropy method to deal with the ambiguity problem .Experimental results show that :statistics-based ap-proach to solve NP and VP structure ambiguity is valid ,closed test accuracy of 80 .1% .