When is multitask learning effective? Semantic sequence prediction under varying data conditions

Héctor Martínez Alonso, Barbara Plank


Abstract
Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine the success of MTL. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary task configurations, amongst which a novel setup, and correlate their impact to data-dependent conditions. Our results show that MTL is not always effective, because significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.
Anthology ID:
E17-1005
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
44–53
Language:
URL:
https://aclanthology.org/E17-1005
DOI:
Bibkey:
Cite (ACL):
Héctor Martínez Alonso and Barbara Plank. 2017. When is multitask learning effective? Semantic sequence prediction under varying data conditions. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 44–53, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
When is multitask learning effective? Semantic sequence prediction under varying data conditions (Martínez Alonso & Plank, EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/E17-1005.pdf
Data
Universal Dependencies