Standard

Improving neural network models for natural language processing in Russian with synonyms. / Galinsky, Ruslan; Alekseev, Anton; Nikolenko, Sergey I.

Proceedings of the AINL FRUCT 2016 Conference. ред. / Andrey Filchenkov; Jan Zizka; Lidia Pivovarova; Sergey Balandin. Institute of Electrical and Electronics Engineers Inc., 2017. 7891856 (Proceedings of the AINL FRUCT 2016 Conference).

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Galinsky, R, Alekseev, A & Nikolenko, SI 2017, Improving neural network models for natural language processing in Russian with synonyms. в A Filchenkov, J Zizka, L Pivovarova & S Balandin (ред.), Proceedings of the AINL FRUCT 2016 Conference., 7891856, Proceedings of the AINL FRUCT 2016 Conference, Institute of Electrical and Electronics Engineers Inc., 5th Artificial Intelligence and Natural Language FRUCT Conference, AINL FRUCT 2016, Saint-Petersburg, Российская Федерация, 10/11/16.

APA

Galinsky, R., Alekseev, A., & Nikolenko, S. I. (2017). Improving neural network models for natural language processing in Russian with synonyms. в A. Filchenkov, J. Zizka, L. Pivovarova, & S. Balandin (Ред.), Proceedings of the AINL FRUCT 2016 Conference [7891856] (Proceedings of the AINL FRUCT 2016 Conference). Institute of Electrical and Electronics Engineers Inc..

Vancouver

Galinsky R, Alekseev A, Nikolenko SI. Improving neural network models for natural language processing in Russian with synonyms. в Filchenkov A, Zizka J, Pivovarova L, Balandin S, Редакторы, Proceedings of the AINL FRUCT 2016 Conference. Institute of Electrical and Electronics Engineers Inc. 2017. 7891856. (Proceedings of the AINL FRUCT 2016 Conference).

Author

Galinsky, Ruslan ; Alekseev, Anton ; Nikolenko, Sergey I. / Improving neural network models for natural language processing in Russian with synonyms. Proceedings of the AINL FRUCT 2016 Conference. Редактор / Andrey Filchenkov ; Jan Zizka ; Lidia Pivovarova ; Sergey Balandin. Institute of Electrical and Electronics Engineers Inc., 2017. (Proceedings of the AINL FRUCT 2016 Conference).

BibTeX

@inproceedings{04775359db3545d2919d1f4f15c0e2f8,
title = "Improving neural network models for natural language processing in Russian with synonyms",
abstract = "Recent advances in deep leaming for natural language processing achieve and improve over state of the art results in many natural language processing tasks. One problem with neural network models, however, is that they require large datasets, including large labeled datasets for the corresponding problems. In this work, we suggest a dala augmentation method based on extending a given dataset with synonyms for the words appearing there. We apply this approach to the morphologically rich Russian language and show improvements for modem neural network NLP models on standard tasks such as sentiment analysis.",
keywords = "natural language processing, data augmentation, character-level models, neural networks",
author = "Ruslan Galinsky and Anton Alekseev and Nikolenko, {Sergey I.}",
note = "Publisher Copyright: {\textcopyright} 2016 FRUCT.; 5th Artificial Intelligence and Natural Language FRUCT Conference, AINL FRUCT 2016 ; Conference date: 10-11-2016 Through 12-11-2016",
year = "2017",
month = apr,
day = "3",
language = "English",
series = "Proceedings of the AINL FRUCT 2016 Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Andrey Filchenkov and Jan Zizka and Lidia Pivovarova and Sergey Balandin",
booktitle = "Proceedings of the AINL FRUCT 2016 Conference",
address = "United States",

}

RIS

TY - GEN

T1 - Improving neural network models for natural language processing in Russian with synonyms

AU - Galinsky, Ruslan

AU - Alekseev, Anton

AU - Nikolenko, Sergey I.

N1 - Publisher Copyright: © 2016 FRUCT.

PY - 2017/4/3

Y1 - 2017/4/3

N2 - Recent advances in deep leaming for natural language processing achieve and improve over state of the art results in many natural language processing tasks. One problem with neural network models, however, is that they require large datasets, including large labeled datasets for the corresponding problems. In this work, we suggest a dala augmentation method based on extending a given dataset with synonyms for the words appearing there. We apply this approach to the morphologically rich Russian language and show improvements for modem neural network NLP models on standard tasks such as sentiment analysis.

AB - Recent advances in deep leaming for natural language processing achieve and improve over state of the art results in many natural language processing tasks. One problem with neural network models, however, is that they require large datasets, including large labeled datasets for the corresponding problems. In this work, we suggest a dala augmentation method based on extending a given dataset with synonyms for the words appearing there. We apply this approach to the morphologically rich Russian language and show improvements for modem neural network NLP models on standard tasks such as sentiment analysis.

KW - natural language processing

KW - data augmentation

KW - character-level models

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=85018414276&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85018414276

T3 - Proceedings of the AINL FRUCT 2016 Conference

BT - Proceedings of the AINL FRUCT 2016 Conference

A2 - Filchenkov, Andrey

A2 - Zizka, Jan

A2 - Pivovarova, Lidia

A2 - Balandin, Sergey

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th Artificial Intelligence and Natural Language FRUCT Conference, AINL FRUCT 2016

Y2 - 10 November 2016 through 12 November 2016

ER -

ID: 95167988