Просмотреть запись

Quick Estimate of Information Decomposition for Text Style Transfer

Электронный научный архив УРФУ

Информация об архиве | Просмотр оригинала
 
 
Поле Значение
 
Заглавие Quick Estimate of Information Decomposition for Text Style Transfer
 
Автор Shibaev, V.
Olbrich, E.
Jost, J.
Yamshchikov, I. P.
 
Тематика INFORMATION DECOMPOSITION
NATURAL LANGUAGE PROCESSING
TEXT STYLE TRANSFER
 
Описание A growing number of papers on style transfer for texts rely on information decomposition. The performance of the resulting systems is usually assessed empirically in terms of the output quality or requires laborious experiments. This paper suggests a straightforward information theoretical framework to assess the quality of information decomposition for latent representations in the context of style transfer. Experimenting with several state-of-the-art models, we demonstrate that such estimates could be used as a fast and straightforward health check for the models instead of more laborious empirical experiments. © 2023 by the authors.
 
Дата 2024-04-05T16:16:16Z
2024-04-05T16:16:16Z
2023
 
Тип Article
Journal article (info:eu-repo/semantics/article)
|info:eu-repo/semantics/publishedVersion
 
Идентификатор Shibaev, V, Olbrich, E, Jost, J & Yamshchikov, IP 2023, 'Quick Estimate of Information Decomposition for Text Style Transfer', Entropy, Том. 25, № 2, 322. https://doi.org/10.3390/e25020322
Shibaev, V., Olbrich, E., Jost, J., & Yamshchikov, I. P. (2023). Quick Estimate of Information Decomposition for Text Style Transfer. Entropy, 25(2), [322]. https://doi.org/10.3390/e25020322
1099-4300
Final
All Open Access, Gold, Green
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85148940853&doi=10.3390%2fe25020322&partnerID=40&md5=212979f6fc941ab779513bab68c67f66
https://www.mdpi.com/1099-4300/25/2/322/pdf?version=1676003466
http://elar.urfu.ru/handle/10995/130230
10.3390/e25020322
85148940853
000944926300001
 
Язык en
 
Права Open access (info:eu-repo/semantics/openAccess)
cc-by
https://creativecommons.org/licenses/by/4.0/
 
Формат application/pdf
 
Издатель MDPI
 
Источник Entropy
Entropy