Government affair problem generation method and device

Abstract

The invention discloses a government affair question generation method and device which can be used in the technical field of artificial intelligence, and the method comprises the steps: obtaining government affair data, open source question and answer data and self-established government affair question and answer text data; inputting the government affair data into a pre-established UNILM network model for training to acquire a pre-trained model, wherein the UNILM network model is pre-established according to Bert Chinese model parameters; inputting the open source question and answer data and the self-established government affair question and answer text data into a pre-training model for fine tuning to obtain a question generation model; and generating government affair questions by using the question generation model. The Chinese data problem generation effect can be improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method and device for generating government affairs questions. Background technique [0002] Question Generation (QG) refers to the generation of related questions based on articles and answers, and the answers can be obtained from articles. The main application scenarios are: in the dialogue system, chatbots actively throw questions to increase the continuity of interaction; automatically generating questions in the construction of question-and-answer and machine reading comprehension datasets can reduce the work of manual disassembly; in the process of constructing question-answer corpus Questions can be automatically generated, which is conducive to the rapid construction of the original question answering data of the question answering system. At present, the government field lacks a unified question-and-answer corpus. In order to reduce the cost of manual ...

AI Technical Summary

Problems solved by technology

At present, the government field lacks a unified question-and-answer corpus. In order to reduce the cost of manual disassembly, the application of question generation technology automatically generates questions for data in the government field to help build data sets.

[0003] The current government problem generation method is not effective for Chinese data problem generation. Therefore, there is an urgent need for a government problem generation scheme that can overcome the above problems.

Images