Synonymous question sentence generation model training method and system and synonymous question sentence generation method

Abstract

The invention also discloses a synonymous question sentence generation model training method and system, wherein the method comprises the steps: obtaining a training sample set which comprises a plurality of synonymous question sentence sets, wherein each synonymous question sentence set in the plurality of synonymous question sentence sets comprises a plurality of question sentence pairs; and training a synonymous question sentence generation model by using the question sentence pairs in the training sample set. The synonymous question sentence generation model is obtained through training, the to-be-expanded question sentence can be directly input into the trained synonymous question sentence generation model during synonymous question sentence expansion, multiple expanded synonymous question sentences can be obtained, manpower and material resources are saved, and expanded sentence patterns are more diversified.

Description

technical field [0001] The invention relates to the field of computer information technology, in particular to a training method and system for generating a synonymous question sentence, and a method for generating a synonymous question sentence. Background technique [0002] The field of natural language processing has developed rapidly in recent years, and the question answering system, as an important content in the field of natural language processing, has also become a hot spot of attention. At this stage, question answering systems are widely used in intelligent customer service, intelligent chat robots, etc. At present, the commonly used question answering system consists of a user interaction module, a knowledge base, a retrieval and sorting module, and an answer processing module. [0003] The closer the user's question is to the question expressed in the knowledge base, the more accurate the question answering system can answer. Otherwise, the Q&A system cannot r...

AI Technical Summary

Problems solved by technology

[0005] The current method of expanding synonymous questions mainly relies on manual replacement of synonyms and subjects, which has the disadvantages of heavy manual workload and inability to generate new sentence patterns.

Images