Abstract: In this paper, a new method using syntactic parsing-based quadratic-bayesian model was proposed to perform question classification in Chinese restricted domain. In this method, firstly, the shallow syntactic parsing on Chinese question sentences is performed. Secondly, the subject-predicate structures of all parsed question sentences, as well as interrogative words and their adjunctive parts, are extracted as the features in our constructed classifier, which greatly reduces the noise information. Thirdly, an advanced Quadratic-Bayesian classification model for question classification in restricted domain is constructed. The experimental results show that the proposed question classification method is feasible in restricted domain with the average classification precisions of coarse classes and fine classes reach 89.66% and 84.13% respectively.

Key words: question classification, quadratic-Bayesian model, question answering system, syntactic parsing

摘要： 针对受限域的特殊性，提出了一种基于句法分析和二次贝叶斯模型的问题分类的新方法。该方法首先利用浅层句法分析的结果，抽取问题的主干部分和疑问词及其附属成分作为分类的特征，大大减少了噪声；然后，提出一种适用于受限域问题分类的改进的二次贝叶斯分类模型，并利用这一模型进行了大量的实验。实验结果表明了这一方法在受限域内的有效性，大类与小类问题的平均分类精度分别达到了89.66%和84.13%。

关键词: 问题分类, 二次贝叶斯模型, 问答系统, 句法分析