Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Vestnik Astrahanskog...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Анализ статистических методов снятия омонимии в текстах на русском языке

Анализ статистических методов снятия омонимии в текстах на русском языке

Abstract

Омонимия осложняет автоматическую обработку текста. Для текстов на английском языке достаточно широко представлены методы снятия омонимии, основанные на использовании вероятностной модели, которые дают достаточно высокую точность. Проблема для текстов на русском языке заключается не только в частеречной омонимии, свойственной текстам на английском языке, но и в морфологической и лексической омонимии. Ввиду того, что составление математической модели для русского языка, который отличается свободным расположением слов в предложении, затруднено, для снятия омонимии в текстах на русском языке большее развитие получили методы, основанные на правилах. В целях выявления результатов работы метода опорных векторов и скрытой марковской модели для снятия частеречной и полной омонимии при обработке текстов на русском языке, проводится эксперимент, в ходе которого используется подкорпус со снятой омонимией национального корпуса русского языка. Показано, что скрытая марковская модель для снятия омонимии в текстах на русском языке работает лучше метода опорных векторов.

Ambiguity complicates text processing. As for English texts there are a number of disambiguation methods based on application of the probability method, which gives high precision results. Regarding to the Russian texts the problem is not only in part-of-speech ambiguity specific for English texts, but also in morphological and lexical ambiguity. In view of the fact that it is difficult to create a mathematical model for Russian language with free order of words in a sentence, the disambiguation methods based on the rules have received a larger development. In order to define the results of support vectors method and hidden Markov’s model of a part-of-speech disambiguation and full disambiguation in Russian texts processing the experiment, which lies in the use of sub-corpus with the disambiguated national corpus of the Russian language, is set up. It is shown that the hidden Markov’s model for disambiguation in Russian texts works better than the method of support vectors.

Keywords

ОМОНИМИЯ, ЧАСТЕРЕЧНАЯ ОМОНИМИЯ, МОРФОЛОГИЧЕСКАЯ ОМОНИМИЯ, ЛЕКСИЧЕСКАЯ ОМОНИМИЯ, МЕТОДЫ СНЯТИЯ ОМОНИМИИ, СКРЫТАЯ МАРКОВСКАЯ МОДЕЛЬ, МЕТОД ОПОРНЫХ ВЕКТОРОВ, HIDDEN MARKOV’S MODEL

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
gold