FIELD: linguistics.
SUBSTANCE: invention relates to extraction and interpretation of information from unstructured text on natural languages, in particular, to machine extraction and interpretation of information in text documents. Machine method of extracting information from text document, involving semantic-syntactic analysis of document sentences to create semantic-syntactic structures of sentences, use of production rules to semantic-syntactic structures, to create set of logic statements on information objects, contained in this document, wherein productional rules are based on linguistic features and lexical-morphological properties of semantic-syntactic structures and ontology domain of sentences, and use of set of logic statements on information objects, contained in document to construct RDF-graph consent with ontology.
EFFECT: technical result is effective analysis of documents for extracting and interpreting information in text documents.
16 cl, 16 dwg
Title | Year | Author | Number |
---|---|---|---|
EXTRACTING INFORMATION FROM STRUCTURED DOCUMENTS CONTAINING TEXT IN NATURAL LANGUAGE | 2015 |
|
RU2607976C1 |
EXTRACTION OF INFORMATION USING ALTERNATIVE VARIANTS OF SEMANTIC-SYNTACTIC ANALYSIS | 2016 |
|
RU2646386C1 |
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 |
DEFINITION OF CONFIDENCE DEGREES RELATED TO ATTRIBUTE VALUES OF INFORMATION OBJECTS | 2016 |
|
RU2640297C2 |
RECOVERY OF TEXT ANNOTATIONS RELATED TO INFORMATION OBJECTS | 2017 |
|
RU2665261C1 |
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 |
METHOD OF EXTRACTING FACTS FROM TEXTS ON NATURAL LANGUAGE | 2016 |
|
RU2637992C1 |
SYSTEM AND METHOD FOR AUTOMATIC CREATION OF TEMPLATES | 2018 |
|
RU2697647C1 |
Authors
Dates
2016-07-20—Published
2015-02-03—Filed