FIELD: data processing.
SUBSTANCE: invention relates to the processing of texts in a natural language. In the method of extracting information from texts in a natural language, a semantic-syntactic analysis of a part of the text in a natural language is performed to obtain a multitude of semantic-syntactic structures, including the first and second alternative semantic-syntactic structures. Many structures are combined to obtain a unified semantic-syntactic structure. Duplicating semantic-syntactic substructures are excluded from the combined structure. Information objects are identified within the specified part of the text by interpreting the unified structure in order to establish the associative connection of tokens, formed by this part of the text with a certain category of information objects. In this case, the interpretation of the combined structure is made, taking into account the value of the quality metric associated with the part of the first alternative structure.
EFFECT: technical result is an increase in the volume of information extraction, taking into account the possible ambiguity of sentences in a natural language and alternative variants of semantic-syntactic analysis.
16 cl, 13 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| EXTRACTION OF INFORMATION FROM SANITARY BLOCKS OF DOCUMENTS USING MICROMODELS ON BASIS OF ONTOLOGY | 2017 |
|
RU2662688C1 |
| USING VERIFIED BY USER DATA FOR TRAINING MODELS OF CONFIDENCE | 2016 |
|
RU2646380C1 |
| SENTIMENT ANALYSIS AT LEVEL OF ASPECTS AND CREATION OF REPORTS USING MACHINE LEARNING METHODS | 2016 |
|
RU2635257C1 |
| CLASSIFICATION OF DOCUMENTS BY LEVELS OF CONFIDENTIALITY | 2019 |
|
RU2732850C1 |
| EXTRACTING INFORMATION FROM STRUCTURED DOCUMENTS CONTAINING TEXT IN NATURAL LANGUAGE | 2015 |
|
RU2607976C1 |
| SYSTEM AND METHOD FOR AUTOMATIC CREATION OF TEMPLATES | 2018 |
|
RU2697647C1 |
| METHOD AND SYSTEM FOR MACHINE EXTRACTION AND INTERPRETATION OF TEXT INFORMATION | 2015 |
|
RU2592396C1 |
| SENTIMENT ANALYSIS AT THE LEVEL OF ASPECTS USING METHODS OF MACHINE LEARNING | 2016 |
|
RU2657173C2 |
| USE OF DEPTH SEMANTIC ANALYSIS OF TEXTS ON NATURAL LANGUAGE FOR CREATION OF TRAINING SAMPLES IN METHODS OF MACHINE TRAINING | 2016 |
|
RU2636098C1 |
| METHOD OF EXTRACTING FACTS FROM TEXTS ON NATURAL LANGUAGE | 2016 |
|
RU2637992C1 |
