When does deep multi-task learning work for loosely related document classification tasks?
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
When does deep multi-task learning work for loosely related document classification tasks? / Kerinec, Emma; Søgaard, Anders; Braud, Chloé.
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics, 2018. s. 1-8.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - When does deep multi-task learning work for loosely related document classification tasks?
AU - Kerinec, Emma
AU - Søgaard, Anders
AU - Braud, Chloé
PY - 2018
Y1 - 2018
N2 - This work aims to contribute to our understandingof when multi-task learning throughparameter sharing in deep neural networksleads to improvements over single-task learning.We focus on the setting of learning fromloosely related tasks, for which no theoreticalguarantees exist. We therefore approach thequestion empirically, studying which propertiesof datasets and single-task learning characteristicscorrelate with improvements frommulti-task learning. We are the first to studythis in a text classification setting and acrossmore than 500 different task pairs.
AB - This work aims to contribute to our understandingof when multi-task learning throughparameter sharing in deep neural networksleads to improvements over single-task learning.We focus on the setting of learning fromloosely related tasks, for which no theoreticalguarantees exist. We therefore approach thequestion empirically, studying which propertiesof datasets and single-task learning characteristicscorrelate with improvements frommulti-task learning. We are the first to studythis in a text classification setting and acrossmore than 500 different task pairs.
M3 - Article in proceedings
SP - 1
EP - 8
BT - Proceedings of the 2018 EMNLP Workshop BlackboxNLP
PB - Association for Computational Linguistics
Y2 - 1 November 2018 through 1 November 2018
ER -
ID: 214759272