Chinese Questions Classification in the Law Domain

Abstract

Question classification is an essential part of Question Answering system(QA). This paper introduces our research work on automatic question classification that depends on the sample set including questions from legal forum. We propose a taxonomy for law question, and divide questions into three main parts: civil, criminal and administrative according to Chinese legal system. We have experimented with four machine learning algorithms: Nearest Neighbors (NN), Naïve Bayes (NB), Logistic Regression (LR) and Support Vector Machines (SVM) using two kinds of features: TF-IDF and word2vec embeddings. Further, we used fastText and adjusted the parameters to get the better results. The research shows high accuracy in Chinese question classification in law domain. Moreover, to the best of our knowledge, our work is the first attempt in this promising domain.