FIELD: physics.
SUBSTANCE: method is done through the stages way of identifying collocations in the texts in natural language. At the same time, a computing device is used to perform semantic-syntactic analysis of text in a natural language for obtaining a multitude of semantic structures. Next, form the initial list of combinations of words in the light of relations defined semantic structures. Make up a list of phrases by applying a heuristic filter to the original list of combinations of words, where the use of a heuristic filter based on quality metrics, representing a function of semantic classes and frequency of relationships between words in composition of phrases. Use a list of phrases to perform a natural language processing.
EFFECT: improving the efficiency of solving tasks of texts in natural language processing.
25 cl, 15 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| TRAINING CLASSIFIERS USED TO EXTRACT INFORMATION FROM NATURAL LANGUAGE TEXTS | 2018 |
|
RU2691855C1 |
| METHOD OF CLUSTERING OF SEARCH RESULTS DEPENDING ON SEMANTICS | 2014 |
|
RU2564629C1 |
| CLASSIFIER TRAINING USED FOR EXTRACTING INFORMATION FROM TEXTS IN NATURAL LANGUAGE | 2018 |
|
RU2681356C1 |
| SYSTEM FOR CREATING DOCUMENTS BASED ON TEXT ANALYSIS ON NATURAL LANGUAGE | 2016 |
|
RU2639655C1 |
| EXTRACTION OF ENTITIES FROM TEXTS IN NATURAL LANGUAGE | 2015 |
|
RU2626555C2 |
| SENTIMENT ANALYSIS AT THE LEVEL OF ASPECTS USING METHODS OF MACHINE LEARNING | 2016 |
|
RU2657173C2 |
| EXPANDING OF INFORMATION SEARCH POSSIBILITY | 2015 |
|
RU2618375C2 |
| METHOD OF EXTRACTING FACTS FROM TEXTS ON NATURAL LANGUAGE | 2016 |
|
RU2637992C1 |
| CREATION OF ONTOLOGIES BASED ON NATURAL LANGUAGE TEXTS ANALYSIS | 2014 |
|
RU2606873C2 |
| SENTIMENT ANALYSIS AT LEVEL OF ASPECTS AND CREATION OF REPORTS USING MACHINE LEARNING METHODS | 2016 |
|
RU2635257C1 |
