介词短语识别中规则与统计方法融合的探讨

Discussion on the Integration of Statistical Learning Method and Artificial Rule Method for Prepositional Phrase Recognition

在介词短语的识别中,统计学习方法和人工规则方法是人们常采用的两种最主要的方法。在浅层句法分析层次上,基于几种典型模式探讨分析构建介词短语识别模型时,规则方法和统计学习方法的有效结合。指出介词短语特征的提取实质是基于语料的语用规则的一种抽象。提出统计学习方法和人工规则方法的有机结合是未来的发展方向。

In recognition of prepositional phrases,statistical learning method and artificial rules method are the two major methods used.Discusses the integration of statistical learning method and artificial rule method for PP recognition based on several typical PP recognition model in the shallow parsing level,and then points out that the feature extraction is an abstract of the pragmatic rules based on corpus.Proposes that the combination of statistical learning methods and artificial rule methods is the future direction of development.