Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation

Qiang Wang, Tong Xiao, Jingbo Zhu


Abstract
The standard neural machine translation model can only decode with the same depth configuration as training. Restricted by this feature, we have to deploy models of various sizes to maintain the same translation latency, because the hardware conditions on different terminal devices (e.g., mobile phones) may vary greatly. Such individual training leads to increased model maintenance costs and slower model iterations, especially for the industry. In this work, we propose to use multi-task learning to train a flexible depth model that can adapt to different depth configurations during inference. Experimental results show that our approach can simultaneously support decoding in 24 depth configurations and is superior to the individual training and another flexible depth model training method——LayerDrop.
Anthology ID:
2020.findings-emnlp.385
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4307–4312
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.findings-emnlp.385/
DOI:
10.18653/v1/2020.findings-emnlp.385
Bibkey:
Cite (ACL):
Qiang Wang, Tong Xiao, and Jingbo Zhu. 2020. Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4307–4312, Online. Association for Computational Linguistics.
Cite (Informal):
Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation (Wang et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.findings-emnlp.385.pdf
Optionalsupplementarymaterial:
 2020.findings-emnlp.385.OptionalSupplementaryMaterial.zip