@InProceedings{martinezalonso-plank:2017:EACLlong,
  author    = {Mart\'{i}nez Alonso, H\'{e}ctor  and  Plank, Barbara},
  title     = {When is multitask learning effective? Semantic sequence prediction under varying data conditions},
  booktitle = {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},
  publisher = {Association for Computational Linguistics},
  pages     = {44--53},
  abstract  = {Multitask learning has been applied successfully to a range of tasks, mostly
	morphosyntactic. However, little is known on \textit{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.},
  url       = {http://www.aclweb.org/anthology/E17-1005}
}