Text augmentation for neural networks

Anna V. Mosolova; Vadim V. Fomin; Ivan Yu Bondarenko

Text augmentation for neural networks

Anna V. Mosolova, Vadim V. Fomin, Ivan Yu Bondarenko

Результат исследования: Научные публикации в периодических изданиях › статья по материалам конференции › рецензирование

Аннотация

This study considers the problem of using small text datasets for learning of neural networks. We explore the method used for image and sound datasets that augments data in order to increase the performance of models trained on it. We propose a method for augmenting that is based on synonymy.

Язык оригинала	английский
Страницы (с-по)	104-109
Число страниц	6
Журнал	CEUR Workshop Proceedings
Том	2268
Состояние	Опубликовано - 2018
Событие	7th International Conference on Analysis of Images, Social Networks and Texts - Supplementary, AIST-SUP 2018 - Moscow, Российская Федерация Продолжительность: 5 июл 2018 → 7 июл 2018

Доступ к документу

Ссылка на публикацию в Scopus

Fingerprint Подробные сведения о темах исследования «Text augmentation for neural networks». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать

@article{b458e5da52294389869eb8192de9d965,

title = "Text augmentation for neural networks",

abstract = "This study considers the problem of using small text datasets for learning of neural networks. We explore the method used for image and sound datasets that augments data in order to increase the performance of models trained on it. We propose a method for augmenting that is based on synonymy.",

keywords = "Neural networks, NLP, Small datasets, Synonymy",

author = "Mosolova, {Anna V.} and Fomin, {Vadim V.} and Bondarenko, {Ivan Yu}",

note = "Publisher Copyright: {\textcopyright} 2017 CEUR-WS. All rights reserved. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 7th International Conference on Analysis of Images, Social Networks and Texts - Supplementary, AIST-SUP 2018 ; Conference date: 05-07-2018 Through 07-07-2018",

year = "2018",

language = "English",

volume = "2268",

pages = "104--109",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

}

Text augmentation for neural networks. / Mosolova, Anna V.; Fomin, Vadim V.; Bondarenko, Ivan Yu.

В: CEUR Workshop Proceedings, Том 2268, 2018, стр. 104-109.

Результат исследования: Научные публикации в периодических изданиях › статья по материалам конференции › рецензирование

TY - JOUR

T1 - Text augmentation for neural networks

AU - Mosolova, Anna V.

AU - Fomin, Vadim V.

AU - Bondarenko, Ivan Yu

PY - 2018

Y1 - 2018

N2 - This study considers the problem of using small text datasets for learning of neural networks. We explore the method used for image and sound datasets that augments data in order to increase the performance of models trained on it. We propose a method for augmenting that is based on synonymy.

AB - This study considers the problem of using small text datasets for learning of neural networks. We explore the method used for image and sound datasets that augments data in order to increase the performance of models trained on it. We propose a method for augmenting that is based on synonymy.

KW - Neural networks

KW - NLP

KW - Small datasets

KW - Synonymy

UR - http://www.scopus.com/inward/record.url?scp=85058949446&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85058949446

VL - 2268

SP - 104

EP - 109

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

T2 - 7th International Conference on Analysis of Images, Social Networks and Texts - Supplementary, AIST-SUP 2018

Y2 - 5 July 2018 through 7 July 2018

ER -