Question Classification in English-Chinese Cross-Language Question Answering: An Integrated Genetic Algorithm and Machine Learning Approach

Abstract

Question classification plays an important role in cross-language question answering (CLQA) systems, while question Informer plays a key role in enhancing question classification for factual question answering. In this paper, we propose an integrated genetic algorithm (GA) and machine learning (ML) approach for question classification in English-Chinese cross-language question answering. To enhance question informer prediction, we use a hybrid method that integrates GA and conditional random fields (CRF) to optimize feature subset selection in a CRF-based question informer prediction model. The proposed approach extends cross-language question classification by using the GA-CRF question informer feature with support vector machines (SVM). The results of evaluations on the NTCIR-6 CLQA question sets demonstrate the efficacy of the approach in improving the accuracy of question classification in English-Chinese cross-language question answering.