FIELD: physics.
SUBSTANCE: in the method for classifying texts in a natural language, semantico-syntactic analysis of text is carried out in the natural language to create a semantic structure that includes a set of semantic classes. The first semantic class is connected with the first value reflecting the value of some attribute of the semantic class. The second semantic class associated with the first semantic class is identified with the specified semantic relations, and it is connected with the second value reflecting the specified attribute of the semantic class. The second value is determined by applying the specified transformation to the first value. The sign of the text in the natural language is calculated on the basis of the first value and the second value and determined using the classifier model with the help of the calculated attribute of the text correlation degree in the natural language with a specific category from a given set of categories.
EFFECT: improving the accuracy of the classification of texts, including in different languages.
20 cl, 15 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| SELECTION OF TEXT CLASSIFIER PARAMETER BASED ON SEMANTIC CHARACTERISTICS | 2016 |
|
RU2628431C1 |
| TRAINING CLASSIFIERS USED TO EXTRACT INFORMATION FROM NATURAL LANGUAGE TEXTS | 2018 |
|
RU2691855C1 |
| CLASSIFIER TRAINING USED FOR EXTRACTING INFORMATION FROM TEXTS IN NATURAL LANGUAGE | 2018 |
|
RU2681356C1 |
| CLASSIFICATION OF DOCUMENTS BY LEVELS OF CONFIDENTIALITY | 2019 |
|
RU2732850C1 |
| USE OF DEPTH SEMANTIC ANALYSIS OF TEXTS ON NATURAL LANGUAGE FOR CREATION OF TRAINING SAMPLES IN METHODS OF MACHINE TRAINING | 2016 |
|
RU2636098C1 |
| EXTRACTING INFORMATION OBJECTS WITH THE HELP OF A CLASSIFIER COMBINATION | 2017 |
|
RU2679988C1 |
| METHOD OF EXTRACTING FACTS FROM TEXTS ON NATURAL LANGUAGE | 2016 |
|
RU2637992C1 |
| RETRIEVAL OF INFORMATION OBJECTS USING A COMBINATION OF CLASSIFIERS ANALYZING LOCAL AND NON-LOCAL SIGNS | 2018 |
|
RU2686000C1 |
| MULTI STAGE RECOGNITION OF THE REPRESENT ESSENTIALS IN TEXTS ON THE NATURAL LANGUAGE ON THE BASIS OF MORPHOLOGICAL AND SEMANTIC SIGNS | 2016 |
|
RU2619193C1 |
| RECOVERY OF TEXT ANNOTATIONS RELATED TO INFORMATION OBJECTS | 2017 |
|
RU2665261C1 |
