Controllable general dialogue model for intention generalization

Abstract

The invention discloses a controllable general dialogue model for intention generalization, and belongs to the field of natural language processing. The system specifically comprises an encoding-decoding structure consisting of a dialogue encoder, an NLU decoder and an NLG decoder, an external database and a rewriter for controlling a text style, for an actual dialogue round of a user, firstly, a dialogue encoder reads a dialogue history, a previous round dialogue state and a current round user input, encoding and feature extraction are carried out to obtain a hidden state, and the hidden state is output to an NLU decoder and an NLG decoder after being preprocessed; the NLU decoder generates a sequence fragment reflecting the intention of the user, maps the sequence fragment into a database checking statement of a database according to the intention of the user, and returns a matching result DB Status by querying an external database; and the NLG decoder generates a reply statement in a natural language form according to the matching result DB Status, and finally feeds back the reply statement to the user. The algorithm complexity is low, the maintenance cost and the expansion cost are reduced, and the prediction efficiency is higher.

Description

technical field [0001] The invention belongs to the field of natural language processing and relates to a dialogue system, in particular to a controllable general dialogue model with generalization intention. Background technique [0002] Human-computer dialogue is an important application in the field of natural language processing. Among them, Task-oriented Dialogue System (TOD) and chatbot (Chatbot) have attracted extensive research in both academia and industry; Chatbot refers to users who do not have a clear purpose. , the system only needs to accompany the user to chat, and does not need to complete a specific goal, and there is often no explicit connection between rounds. TOD means that the user has a clear purpose, and the system needs to access an external database through limited dialogue rounds to guide the user to complete the task and achieve the purpose, such as querying the weather, recommending attractions, and booking hotels. In actual development, related ...

AI Technical Summary

Problems solved by technology

These dialogue models are completely independent in the data structure of the corpus used, the design of the network, and the training of model parameters, which means that heterogeneous dialogue data sets are trained separately on the heterogeneous network structure, and there is no parameter sharing mechanism. To learn the inherent semantic features and knowledge between corpora; and the model parameters are very large, not light enough and convenient for transfer learning

Images