Identifying beneficial task relations for multi-task learning in deep neural networks
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Identifying beneficial task relations for multi-task learning in deep neural networks. / Bingel, Joachim; Søgaard, Anders.
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: volume 2, short papers. Vol. 2 Association for Computational Linguistics, 2017. p. 164-169.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Identifying beneficial task relations for multi-task learning in deep neural networks
AU - Bingel, Joachim
AU - Søgaard, Anders
N1 - Conference code: 15
PY - 2017
Y1 - 2017
N2 - Multi-task learning (MTL) in deep neural networks for NLP has recently received increasing interest due to some compelling benefits, including its potential to efficiently regularize models and to reduce the need for labeled data. While it has brought significant improvements in a number of NLP tasks, mixed results have been reported, and little is known about the conditions under which MTL leads to gains in NLP. This paper sheds light on the specific task relations that can lead to gains from MTL models over single-task setups.
AB - Multi-task learning (MTL) in deep neural networks for NLP has recently received increasing interest due to some compelling benefits, including its potential to efficiently regularize models and to reduce the need for labeled data. While it has brought significant improvements in a number of NLP tasks, mixed results have been reported, and little is known about the conditions under which MTL leads to gains in NLP. This paper sheds light on the specific task relations that can lead to gains from MTL models over single-task setups.
UR - http://www.scopus.com/inward/record.url?scp=85021633901&partnerID=8YFLogxK
M3 - Article in proceedings
AN - SCOPUS:85021633901
VL - 2
SP - 164
EP - 169
BT - Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics
Y2 - 3 April 2017 through 7 April 2017
ER -
ID: 184142439