A Survey of Extractive Question Answering

Extractive question answering is one of the most important tasks in natural language processing (NLP) which has high research value. In order to sort out its development process, in this paper, it was divided into two categories roughly in this paper: single-span extractive question answering and multispan extractive question answering, which are divided according to the number of spans. Studies on the two classifications are briefly described in the following context, following a certain logical relationship. And single-span extractive question is further divided into four categories to make a more detailed introduction. In addition, some works that can be done in the future is mentioned.