An Integrated Knowledge-based and Machine Learning Approach for Chinese Question Classification

Abstract

Question classification plays an important role in question-answering systems. Chinese question classification is the process that analyzes a question and labels it based on its question type and expected answer type. In this paper, we propose an integrated knowledge-based and machine learning approach for Chinese question classification that focuses on factoid question answering. We develop a Chinese question classification scheme for CLQA C-C (cross language question answering Chinese to Chinese) factoid question answering, and define a coarse-grained and fine-grained classification taxonomy for a Chinese question-answering system. We adopt INFOMAP inference engine to support the knowledge-based approach for Chinese questions, which can be formulated as templates and use SVM (support vector machines) as the machine learning approach for large collections of labeled Chinese questions. Our experimental results show that the accuracy of Chinese question classification using INFOMAP alone is 88% and 73.5% with SVM alone. In contrast, classification based on a hybrid approach that incorporates SVM and INFOMAP yields an accuracy rate of 92%.