%0 Generic %1 hashimoto2016joint %A Hashimoto, Kazuma %A Xiong, Caiming %A Tsuruoka, Yoshimasa %A Socher, Richard %D 2016 %K %T A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks %U http://arxiv.org/abs/1611.01587 %X 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.

@misc{hashimoto2016joint, 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.}, added-at = {2018-11-27T09:57:13.000+0100}, author = {Hashimoto, Kazuma and Xiong, Caiming and Tsuruoka, Yoshimasa and Socher, Richard}, biburl = {https://www.bibsonomy.org/bibtex/21ecd28e778c5d57b6a9ca3559754323a/florianpircher}, interhash = {0026f760ecbd215930337535ac042fc4}, intrahash = {1ecd28e778c5d57b6a9ca3559754323a}, keywords = {}, note = {cite arxiv:1611.01587Comment: Accepted as a full paper at the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017)}, timestamp = {2018-11-27T09:57:13.000+0100}, title = {A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks}, url = {http://arxiv.org/abs/1611.01587}, year = 2016 }