Identifying beneficial task relations for multi-task learning in deep neural networks Identifying beneficial task relations for multi-task learning in deep neural networks
Paper summary The authors investigate the benefit of different task combinations when performing multi-task learning. https://i.imgur.com/VmD2ioS.png They experiment with all possible pairs of 10 sequence labeling datasets, switching between the datasets during training. They find that multi-task learning helps more when the main task quickly plateaus while the auxiliary task does not, likely helping the model out of local minima. There does not seem to be any auxiliary task that would help on all main tasks, but chunking and semantic tagging seem to perform best.
aclanthology.info
sci-hub
scholar.google.com
Identifying beneficial task relations for multi-task learning in deep neural networks
Søgaard, Anders and Bingel, Joachim
Association for Computational Linguistics EACL (2) - 2017 via Local Bibsonomy
Keywords: dblp


Summary by Marek Rei 6 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and