Model training method, dialogue generation method and device, equipment and medium

Abstract

The invention discloses a dialogue generation model training method, which comprises the following steps: obtaining a dialogue data set, the dialogue data in the dialogue data set comprising questionsand annotation replies corresponding to the questions; based on the questions in the dialogue data set, obtaining the coded representation of the question through an encoder in a constructed dialoguegeneration model; fusing the coded representation of the question and knowledge information of transfer learning of the question from a knowledge base question and answer model through a decoder in the dialogue generation model to obtain a prediction reply corresponding to the question output by the dialogue generation model; and determining a loss function based on the prediction reply and the annotation reply corresponding to the question, and adjusting parameters of the dialogue generation model through the loss function until the loss function of the dialogue generation model is convergent. According to the method, the knowledge information can be better fused by the model, so that the dialogue generation accuracy and reasonability are improved. The invention further discloses a dialogue generation method and device, equipment and a medium.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular to a dialog generation model training method, a dialog generation method, a device, a device, and a computer storage medium. Background technique [0002] The open-domain dialogue generation task refers to the generation of corresponding responses by machines based on dialogue questions in the open domain. Due to its powerful functions and wide application scenarios, it has recently received more and more attention and research. [0003] At present, the open-domain dialogue generation task usually relies on the dialogue generation model to achieve, and in order to enable the dialogue generation model to generate more informative and more reasonable replies, industry research proposes that the integration of external common sense knowledge base information in the open-domain dialogue generation task can This makes the generated reply more reasonable and informa...

AI Technical Summary

Problems solved by technology

[0004] However, the method of fusing the information of the external commonsense knowledge base proposed in the related art is a relatively coarse-grained fusion, which only considers the integration of the entity in the question sentence with the external knowledge into the reply generation, and does not consider the finer-grained The integration of external knowledge does not consider the accuracy and rationality of external knowledge. This fusion effect is not good and cannot meet the needs of practical applications.

Images