Efficient Inference For Multilingual Neural Machine Translation · The Large Language Model Bible Contribute to LLM-Bible

Efficient Inference For Multilingual Neural Machine Translation

Berard Alexandre, Lee Dain, Clinchant Stéphane, Jung Kweonwoo, Nikoulina Vassilina. Arxiv 2021

[Paper]    
Applications Model Architecture Security

Multilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work, we consider several ways to make multilingual NMT faster at inference without degrading its quality. We experiment with several “light decoder” architectures in two 20-language multi-parallel settings: small-scale on TED Talks and large-scale on ParaCrawl. Our experiments demonstrate that combining a shallow decoder with vocabulary filtering leads to more than twice faster inference with no loss in translation quality. We validate our findings with BLEU and chrF (on 380 language pairs), robustness evaluation and human evaluation.

Similar Work