When is multitask learning effective? Semantic sequence prediction under varying data conditions - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

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.
Fichier principal
Vignette du fichier
eacl2017.pdf (306.92 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01677427 , version 1 (08-01-2018)

Identifiers

  • HAL Id : hal-01677427 , version 1

Cite

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⟩
263 View
135 Download

Share

Gmail Facebook X LinkedIn More