Bilingual emotional dialogue generation system based on interactive decoding

Abstract

The invention relates to a bilingual emotional dialogue generation system based on interactive decoding. Multi-language information complementation is adopted, and high-quality emotion replies can begenerated. The traditional emotional dialogue generation model is trained and tested by using a single corpus, a bilingual material (Chinese and English) is used for training and testing the model, and in the process of generating emotion replies, a Chinese decoder and an English decoder carry out information complementation through an internal and external interaction mechanism. Wherein the internal interaction is used for mining dynamic context information between answers in different languages by virtue of an auxiliary effect of redundant information between languages, and generating replies by utilizing more sufficient information, so that the confusion degree is reduced, the quality of answer contents is improved, and high-quality emotion replies are generated; after the context information of the other decoder is fully considered in external interaction, emotion words or common words are selected and generated through the type selector, and grammatical rationality and emotion naturalness of reply are balanced.

Description

technical field [0001] The embodiment of the present invention relates to the technical field of language processing, in particular to a bilingual emotional dialogue generation system based on interactive decoding. Background technique [0002] At present, the application range of man-machine dialogue system is getting wider and wider. For example, in the medical field, dialogue systems can provide health information services to patients and consumers more conveniently; in the field of e-commerce, task-oriented dialogue systems can assist customers to complete online shopping. [0003] With the importance of emotion in improving conversation quality highlighted, the field of emotional dialogue generation has gradually attracted people's attention. The researchers found that the introduction of emotional factors in the dialogue process can improve the user's sense of experience. In order to make the dialogue system more intelligent and the generated responses to meet people...

AI Technical Summary

Problems solved by technology

[0006] Although the above dialogue generation model has noticed the importance of emotional factors in the dialogue system, the effect achieved is not satisfactory. It cannot well mine the emotional elements in the dialogue content, and the emotional intensity of the generated answers is uncontrollable and not detailed. It is difficult to give full play to the role of emotion in dialogue, and the generated sentences appear very blunt and dull

Therefore, the dialogue systems that have been proposed so far need to be improved

Images