FIELD: computer technology.
SUBSTANCE: invention relates to the field of computer technology for searching and correcting errors in natural language texts. The effect is achieved due to the modular organization of the system: independent connection to it of modules for searching and correcting errors of various nature (heuristic and neural network); the ability to connect optional modules to correct specific types of errors; improvements in both approaches to GEC compared to existing samples - in particular, the use of a heuristic approach in preparing data for training a neural network module and a machine learning approach when collecting data for a heuristic module; iterative additional training of the neural network model, taking into account expert markup; effective convergence of the results (errors found) received from various modules by the control module of the system, with the resolution of possible conflicts between them.
EFFECT: increasing the accuracy and completeness of identifying grammatical, speech, stylistic errors.
13 cl, 7 dwg, 3 tbl
| Title | Year | Author | Number | 
|---|---|---|---|
| METHOD AND SYSTEM FOR GENERATING TEXT | 2023 | 
 | RU2817524C1 | 
| SYSTEM AND METHOD FOR CORRECTING SPELLING ERRORS | 2020 | 
 | RU2753183C1 | 
| SYSTEM FOR AUTOMATIC UPDATING AND GENERATION OF TECHNIQUES FOR IMPLEMENTING COMPUTER ATTACKS FOR INFORMATION SECURITY SYSTEM | 2023 | 
 | RU2809929C1 | 
| METHOD AND SYSTEM FOR DIGITAL ASSISTANT TEXT GENERATION | 2022 | 
 | RU2796208C1 | 
| METHOD FOR DISPLAYING SUBTITLES IN THE PROCESS OF PLAYING MEDIA CONTENT (OPTIONS) | 2017 | 
 | RU2668721C1 | 
| METHOD AND SYSTEM FOR GENERATION OF ARTICLES IN NATURAL LANGUAGE DICTIONARY | 2014 | 
 | RU2639280C2 | 
| METHOD FOR CONTROLLING A DIALOGUE AND NATURAL LANGUAGE RECOGNITION SYSTEM IN A PLATFORM OF VIRTUAL ASSISTANTS | 2020 | 
 | RU2759090C1 | 
| METHOD AND SYSTEM FOR PARAPHRASING TEXT | 2023 | 
 | RU2814808C1 | 
| METHOD OF TEACHING FOREIGN LANGUAGE | 2010 | 
 | RU2422911C1 | 
| RETRIEVAL OF INFORMATION OBJECTS USING A COMBINATION OF CLASSIFIERS ANALYZING LOCAL AND NON-LOCAL SIGNS | 2018 | 
 | RU2686000C1 | 
Authors
Dates
2022-12-05—Published
2021-12-27—Filed