Mind the Gap: Diverse NMT Models for Resource-Constrained Environments
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511578" target="_blank" >RIV/00216208:11320/25:10511578 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2025.nodalida-1.21/" target="_blank" >https://aclanthology.org/2025.nodalida-1.21/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Mind the Gap: Diverse NMT Models for Resource-Constrained Environments
Original language description
We present fast Neural Machine Translation models for 17 diverse languages, developed using Sequence-level Knowledge Distillation. Our selected languages span multiple language families and scripts, including low-resource languages. The distilled models achieve comparable performance while being 10x times faster than transformer-base and 35x times faster than transformer-big architectures. Our experiments reveal that teacher model quality and capacity strongly influence the distillation success, as well as the language script. We also explore the effectiveness of multilingual students. We release publicly our code and models in our Github repository.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
R - Projekt Ramcoveho programu EK
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies
ISBN
978-9908-53-109-0
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
209-216
Publisher name
University of Tartu Library
Place of publication
Tallinn, Estonia
Event location
Tallinn, Estonia
Event date
Mar 2, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—