When does deep multi-task learning work for loosely related document classification tasks?

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

T2 - 2018 EMNLP Workshop BlackboxNLP

Y2 - 1 November 2018 through 1 November 2018

ER -