Multi-round dialogue rewriting method and system based on text editing and grammar error correction

Abstract

The invention discloses a multi-round dialogue rewriting method and system based on text editing and grammar error correction, and the method comprises the steps: carrying out word-level labeling of a collected dialogue data text through a text labeling algorithm, generating text labeling data, and carrying out fine adjustment of a deformation-based bidirectional coding representation model, so as to obtain a sequence labeling model; editing dialogue history and incomplete statements according to the classification label of each word in the prediction sequence of the model, and finally carrying out grammar error correction modeling on the rewritten text to improve the fluency of the statements. According to the method, the accuracy of multi-round dialogue rewriting can be improved, the problems of anaphora and omission in a dialogue system are effectively solved by utilizing a text editing and grammar error correction method in dialogues, and the integrity of dialogue statements is improved.

Description

technical field [0001] The present invention relates to a technology for multi-round dialogue rewriting in an intelligent dialogue system, in particular to a multi-round dialogue rewriting (Dialogue Utterance Rewritten via SequenceEditing, DuReSE) method and system based on text editing and grammatical error correction. Background technique [0002] In recent years, with the development of natural language processing (nlp) technology, more and more enterprises use intelligent chatbots to replace human responses. Taking the user's inquiry and the corresponding reply of the robot as a round of dialogue, the reply generation method of a single round of dialogue is very mature, but users usually have multiple rounds of dialogue to achieve their goals. During multiple rounds of dialogue, the user often enters dialogue sentences with incomplete information (reference or omission), that is, there are pronouns pointing to part of the information in the dialogue history or omissions ...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at solving the problem of incomplete multi-round dialogue information in the prior art without considering the high overlap between the original text and the target text, and proposes a multi-round dialogue rewriting method and system based on text editing and grammatical error correction, which can improve The accuracy of rewriting multiple rounds of dialogues, using text editing and grammatical error correction methods in the dialogues, effectively solves the problem of reference and omission in the dialogue system, and improves the integrity of dialogue sentences

Images