Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models

27 October 2022

Papers citing "Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models"

3 / 3 papers shown

Title
What Do Compressed Multilingual Machine Translation Models Forget? Alireza Mohammadshahi Vassilina Nikoulina Alexandre Berard Caroline Brun James Henderson Laurent Besacier AI4CE 22 9 0 22 May 2022
I-BERT: Integer-only BERT Quantization Sehoon Kim A. Gholami Z. Yao Michael W. Mahoney Kurt Keutzer MQ 83 332 0 05 Jan 2021
The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MT Jörg Tiedemann 160 163 0 13 Oct 2020