Skip to Main content Skip to Navigation
Conference papers

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

Abstract : Multitask learning has been applied successfully to a range of tasks, mostly mor-phosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine its success. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary tasks, amongst which a novel setup, and correlate their impact to data-dependent conditions. Our results show that MTL is not always effective, significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.
Document type :
Conference papers
Complete list of metadata

Cited literature [37 references]  Display  Hide  Download

https://hal.inria.fr/hal-01677427
Contributor : Benoît Sagot <>
Submitted on : Monday, January 8, 2018 - 3:20:46 PM
Last modification on : Friday, March 27, 2020 - 3:46:51 AM

File

eacl2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01677427, version 1

Collections

Citation

Hector Martinez Alonso, Barbara Plank. When is multitask learning effective? Semantic sequence prediction under varying data conditions. EACL 2017 - 15th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2017, Valencia, Spain. pp.1-10. ⟨hal-01677427⟩

Share

Metrics

Record views

366

Files downloads

318