Multitask learning for semantic sequence prediction under varying data conditions

14 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Multi-Task Learning for Sequence Tagging: An Empirical Study (2018, methodology): “MTL has been validated in recent work, mostly where auxiliary tasks are used to improve the performance on a target task, for example, in sequence tagging (Søgaard and Goldberg, 2016; Bjerva et al., 2016; Plank et al., 2016; Alonso and Plank, 2017; Bingel and Søgaard, 2017).”
Diagnostic classification and symbolic guidance to understand and improve recurrent neural networks (2017, background): “…has been successfully applied to several different natural language processing tasks [e.g. Collobert and Weston, 2008, Søgaard and Goldberg, 2016], but shows mixed results in general, due to the intricacy of finding appropriate auxiliary tasks [Bingel and Søgaard, 2017, Alonso and Plank, 2016].”