Text generation method, text generation device, and learning-completed model

Abstract

The invention relates to a text generation method, a text generation device, and a learning-completed model, which cope with the complication of processing while reducing the difficulty of constructing learning data. A replacement information collection unit determines a role of an auxiliary replacer; an auxiliary replacer teacher data generation unit generates replacement teacher data used for machine learning of the auxiliary replacer based on a reference result of a replacement information DB; an auxiliary replacer generation unit generates the auxiliary replacer based on a replacement teacher data DB; an auxiliary replacer and text generator coupling unit couples the auxiliary replacer generated by the auxiliary replacer generation unit with a text generator that has not performed learning; a text generation information collection unit collects before-generation information and after-generation information of a text; a text generator teacher data generation unit generates generation teacher data used for machine learning of the text generator based on a reference result of a generation information DB; and a text generator generation unit generates a text generator based on a generation teacher data DB.

Description

technical field [0001] The present invention relates to a text generation method, a text generation device and a learned model. Background technique [0002] In many systems related to natural language processing, it is necessary to identify whether two texts have the same meaning or intent. For example, consider a question-response system that has a pair of question text and answer text, accepts input from a user, finds a question text suitable for the input, and outputs an answer corresponding to the question text. [0003] The input from the user does not necessarily have to be the same text as the question text of the question answering system. Even if the question-response system has a pairing of "May I ask the location of the station" as the question text and "200 meters to the north" as the answer text, there may be cases where the input from the user is not "May I ask the location of the station" but "I want to know the location of the station" The case for such a ...

AI Technical Summary

Problems solved by technology

[0004] Not limited to the above-mentioned example, due to changes in input conjugations or other words with the same meaning, in the question-response system, although there are answer texts, there may be a problem that the input from the user cannot be associated with the corresponding question text. result

Images