Question answering is one of the oldest and challenging tasks in natural language processing. The goal is
to build systems that are able to automatically answer questions posed by human in a natural language.
This survey focuses on question classification task, which is a subtask in question answering. Question
classification aims to associate a category to each question, typically representing the semantic class of its
answer. It is of major importance in the question answering process, since it is the basis of several key
decisions. This survey presents basic introduction about question answering, some approaches for
question classification, including rule-based approach and machine learning approach, and the accuracy
comparison among them.