Complex approach towards algoritm learning for anaphora resolution in Russian language

O. A. Gureenkova; T. V. Batura; A. A. Kozlova; A. N. Svischev

Complex approach towards algoritm learning for anaphora resolution in Russian language

O. A. Gureenkova, T. V. Batura, A. A. Kozlova, A. N. Svischev

Результат исследования: Научные публикации в периодических изданиях › статья › рецензирование

Аннотация

The paper considers applying of ensemble algorithm based on rules and machine learning for anaphora resolution in Russian language. Ensemble presents combination of formal rules, a machine learning algorithm Extra Trees and an algorithm for working with imbalanced learning sets Balance Cascade. Complexity of the approach lies in generation of complex features from rules and vectorization of syntactic context, with context data obtained from algorithms mystem (Yandex), SyntaxNet (Google) and Word2Vec.

Язык оригинала	английский
Страницы (с-по)	89-97
Число страниц	9
Журнал	Komp'juternaja Lingvistika i Intellektual'nye Tehnologii
Том	1
Номер выпуска	16
Состояние	Опубликовано - 2017

Предметные области OECD FOS+WOS

6.02 ЯЗЫК И ЛИТЕРАТУРА

Доступ к документу

Link to publication in Scopus

Fingerprint

Подробные сведения о темах исследования «Complex approach towards algoritm learning for anaphora resolution in Russian language». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать

@article{41cbe4f9bfaf4d668c29e02337da80d6,

title = "Complex approach towards algoritm learning for anaphora resolution in Russian language",

abstract = "The paper considers applying of ensemble algorithm based on rules and machine learning for anaphora resolution in Russian language. Ensemble presents combination of formal rules, a machine learning algorithm Extra Trees and an algorithm for working with imbalanced learning sets Balance Cascade. Complexity of the approach lies in generation of complex features from rules and vectorization of syntactic context, with context data obtained from algorithms mystem (Yandex), SyntaxNet (Google) and Word2Vec.",

keywords = "Anaphora, Antecedent, Balance Cascade, Cataphora, Extra Trees, Imbalanced set, Machine learning, Random forest, SyntaxNet, Word2Vec",

author = "Gureenkova, {O. A.} and Batura, {T. V.} and Kozlova, {A. A.} and Svischev, {A. N.}",

year = "2017",

language = "English",

volume = "1",

pages = "89--97",

journal = "Komp'juternaja Lingvistika i Intellektual'nye Tehnologii",

issn = "2221-7932",

number = "16",

}

Complex approach towards algoritm learning for anaphora resolution in Russian language. / Gureenkova, O. A.; Batura, T. V.; Kozlova, A. A.; Svischev, A. N.

В: Komp'juternaja Lingvistika i Intellektual'nye Tehnologii, Том 1, № 16, 2017, стр. 89-97.

Результат исследования: Научные публикации в периодических изданиях › статья › рецензирование

TY - JOUR

T1 - Complex approach towards algoritm learning for anaphora resolution in Russian language

AU - Gureenkova, O. A.

AU - Batura, T. V.

AU - Kozlova, A. A.

AU - Svischev, A. N.

PY - 2017

Y1 - 2017

N2 - The paper considers applying of ensemble algorithm based on rules and machine learning for anaphora resolution in Russian language. Ensemble presents combination of formal rules, a machine learning algorithm Extra Trees and an algorithm for working with imbalanced learning sets Balance Cascade. Complexity of the approach lies in generation of complex features from rules and vectorization of syntactic context, with context data obtained from algorithms mystem (Yandex), SyntaxNet (Google) and Word2Vec.

AB - The paper considers applying of ensemble algorithm based on rules and machine learning for anaphora resolution in Russian language. Ensemble presents combination of formal rules, a machine learning algorithm Extra Trees and an algorithm for working with imbalanced learning sets Balance Cascade. Complexity of the approach lies in generation of complex features from rules and vectorization of syntactic context, with context data obtained from algorithms mystem (Yandex), SyntaxNet (Google) and Word2Vec.

KW - Anaphora

KW - Antecedent

KW - Balance Cascade

KW - Cataphora

KW - Extra Trees

KW - Imbalanced set

KW - Machine learning

KW - Random forest

KW - SyntaxNet

KW - Word2Vec

UR - http://www.scopus.com/inward/record.url?scp=85021792831&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85021792831

VL - 1

SP - 89

EP - 97

JO - Komp'juternaja Lingvistika i Intellektual'nye Tehnologii

JF - Komp'juternaja Lingvistika i Intellektual'nye Tehnologii

SN - 2221-7932

IS - 16

ER -