Year: 2021
Type: conference-paper
Abstract: 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 20language 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 ×2 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.
Authors: Alexandre Berard, Dain Lee, Stephane Clinchant, Kweonwoo Jung, Vassilina Nikoulina
Institutions: Université de Lille, Naver (South Korea)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3201215554