WUST System at NTCIR-12 QALab-2 Task

This paper describes our question answering system at NTCIR-12 on QALab-2 task, which requires solving the history questions of Japanese university entrance exams and their corresponding English translations. Wikipedia of English edition is main external knowledge base for our system. We first retrieve the documents and sentences related to the question from Wikipedia. Then, the classification model has been constructed based on SVM (Support Vector Machine) in order to solve the question by choosing right or wrong sentence in multiple choice-type questions for the National Center Test, and five kinds of features about questions and choices have been extracted as inputs to the model. Finally, we choose the answer according to the score of each choice.