Year: 2025
Type: conference-paper
Abstract: Language tagging, a method whereby source and target inputs are prefixed with a unique language token, has become the de facto standard for conditioning Multilingual Neural Machine Translation (MNMT) models on specific language directions.This conditioning can manifest effective zero-shot translation abilities in MT models at scale for many languages.Expanding on previous work, we propose a novel method of language tagging for MNMT, injection, in which the embedded representation of a language token is concatenated to the input of every linear layer.We explore a variety of different tagging methods, with and without injection, showing that injection improves zeroshot translation performance with up to a 2+ BLEU score point gain for certain language directions in our dataset.
Authors: Jay Orten, Ammon Shurtz, Nancy Fulda, Stephen D. Richardson
Institution: Brigham Young University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412889394