1 |
deepQuest-py: large and distilled models for quality estimation
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations ; 382 ; 389 (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Knowledge distillation for quality estimation
|
|
|
|
In: 5091 ; 5099 (2021)
|
|
Abstract:
© 2021 The Authors. Published by ACL. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: https://aclanthology.org/2021.findings-acl.452 ; Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent success in QE stems from the use of multilingual pre-trained representations, where very large models lead to impressive results. However, the inference time, disk and memory requirements of such models do not allow for wide usage in the real world. Models trained on distilled pre-trained representations remain prohibitively large for many usage scenarios. We instead propose to directly transfer knowledge from a strong QE teacher model to a much smaller model with a different, shallower architecture. We show that this approach, in combination with data augmentation, leads to light-weight QE models that perform competitively with distilled pre-trained representations with 8x fewer parameters.
|
|
Keyword:
knowledge distillation; machine translation; quality estimation
|
|
URL: https://doi.org/10.18653/v1/2021.findings-acl.452 http://hdl.handle.net/2436/624102
|
|
BASE
|
|
Hide details
|
|
|
|