BAM! Born-Again Multi-Task Networks for Natural Language Understanding

ACL 2019

BAM! Born-Again Multi-Task Networks for Natural Language Understanding

Feb 02, 2021
|
30 views
|
Details
Abstract: It can be challenging to train multi-task neural networks that outperform or even match their single-task counterparts. To help address this, we propose using knowledge distillation where single-task models teach a multi-task model. We enhance this training with teacher annealing, a novel method that gradually transitions the model from distillation to supervised learning, helping the multi-task model surpass its single-task teachers. We evaluate our approach by multi-task fine-tuning BERT on the GLUE benchmark. Our method consistently improves over standard single-task and multi-task training. Authors: Kevin Clark, Minh-Thang Luong, Urvashi Khandelwal, Christopher D. Manning, Quoc V. Le (Stanford University, Google Brain)

Comments
loading...