Question generation method and device and storage medium

Abstract

The invention provides a question generation method and device and a storage medium, and the method comprises the steps: importing a triple which comprises a paragraph vector group, an original question vector group and an answer vector group; splicing the paragraph vector group and the answer vector group to obtain a spliced vector group; constructing a training model, and performing training analysis on the spliced vector group and the original problem vector group through the training model to obtain a trained problem vector group; and updating and analyzing the training model according to the trained problem vector group and the original problem vector group to obtain a final model. According to the method and device, the matching degree between the generated question and the context and the answer is enhanced, the obtained final model can generate and process the questions of the paragraph vector group to be tested and the answer vector group to be tested to obtain the question generation result, convergence is easier, the problem that the generated question is not highly matched with the given context and answer is solved, and the robustness is enhanced.

Description

technical field [0001] The present invention mainly relates to the technical field of text processing, and in particular relates to a question generation method, device and storage medium. Background technique [0002] Natural question generation (Natura l Quest i on Generat ion) is question generation, which has many applications, such as improving automatic question answering tasks, generating related exercises for educational purposes, etc. Traditional question generation relies on heuristic rules and artificially given templates, this method has low versatility and low scalability. In recent years, the neural network method (NN) is mainly used to perform this task, and good achievements have been made, but there are still problems such as the low matching between the generated questions and the given context and answers. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a question generation method, device and...

AI Technical Summary

Problems solved by technology

[0002] Natural question generation (Natura l Quest i on Generat ion) is question generation, which has many applications, such as improving automatic question answering tasks, generating related exercises for educational purposes, etc. Traditional question generation relies on heuristic rules and artificially given template, this method has low versatility and low scalability

In recent years, the neural network method (NN) is mainly used to perform this task, and good achievements have been made, but there are still problems such as the low matching between the generated questions and the given context and answers.

Images