Training method, training device, dialogue method and dialogue system of dialogue model

Abstract

The invention discloses a training method, a training device, a dialogue method and a dialogue system of a dialogue model. The training method comprises the steps of total error constructing, whereina total error function comprising a first error of a natural language understanding model and a second error of a strategy generating model are constructed simultaneously; joint training, wherein withthe target of reducing the total error function, a corpus sample is utilized to jointly train the natural language understanding model and the strategy generating model, input of the natural languageunderstanding model is dialogue sentences, output of the natural language understanding model is internal representation obtained by analyzing the dialogue sentences, input of the strategy generatingmodel at least comprises the output of the natural language understanding model, and output of the strategy generating model is motions aiming at the dialogue sentence. Compared with the prior art, when an error occurs on the natural language understanding model or the strategy generating model, the system can normally conduct dialogues, and the error transferring problem in a traditional methodcaused when the natural language understanding model and a dialogue management model are modeled respectively is solved.

Description

technical field [0001] The invention relates to the field of man-machine dialogue, in particular to a dialogue model training method, training device, dialogue method and dialogue system. Background technique [0002] Traditional dialogue systems can generally be summarized into the following three stages: [0003] 1) The user inputs through text or voice, and the natural language understanding (NLU) module analyzes the user's input to obtain a structured internal representation. [0004] 2) The dialogue management (DM) module receives the structured internal representation, updates it according to the historical system state, obtains the latest system state, and then selects the system action corresponding to the latest system state according to the dialogue strategy formulated in advance, to the next module. [0005] 3) Finally, the Natural Language Generation (NLG) module is responsible for converting system actions into natural language or speech output that humans can...

AI Technical Summary

Problems solved by technology

Since the natural language understanding module and the dialogue management module are modeled separately in traditional dialogue systems, errors in both will affect the final result. For example, when there is a problem with the natural language understanding module, the error generated by the natural language understanding module will be Passed to the dialogue management module, so that the dialogue management module cannot be carried out normally

In the actual process, errors in the natural language understanding module or dialogue management module are unavoidable, so the traditional training method obviously cannot solve this error transfer problem

Images