@InProceedings{hashimoto-EtAl:2017:EMNLP2017,
  author    = {Hashimoto, Kazuma  and  xiong, caiming  and  Tsuruoka, Yoshimasa  and  Socher, Richard},
  title     = {A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1923--1933},
  abstract  = {Transfer and multi-task learning have traditionally focused on either a single
	source-target pair or very few, similar tasks.
	Ideally, the linguistic levels of morphology, syntax and semantics would
	benefit each other by being trained in a single model.
	We introduce a joint many-task model together with a strategy for successively
	growing its depth to solve increasingly complex tasks.
	Higher layers include shortcut connections to lower-level task predictions to
	reflect linguistic hierarchies.
	We use a simple regularization term to allow for optimizing all model weights
	to improve one task's loss without exhibiting catastrophic interference of the
	other tasks.
	Our single end-to-end model obtains state-of-the-art or competitive results on
	five different tasks from tagging, parsing, relatedness, and entailment tasks.},
  url       = {https://www.aclweb.org/anthology/D17-1206}
}