Sirvi Autor "Gibert, Ona de" järgi

Nüüd näidatakse 1 - 2 2

Mind the Gap: Diverse NMT Models for Resource-Constrained Environments
(University of Tartu Library, 2025-03) Gibert, Ona de; O'Brien, Dayyán; Variš, Dušan; Tiedemann, Jörg; Johansson, Richard; Stymne, Sara
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: anonymised.
OpusDistillery: A Configurable End-to-End Pipeline for Systematic Multilingual Distillation of Open NMT Models
(University of Tartu Library, 2025-03) Gibert, Ona de; Nieminen, Tommi; Scherrer, Yves; Tiedemann, Jörg; Johansson, Richard; Stymne, Sara
In this work, we introduce OpusDistillery, a novel framework to streamline the Knowledge Distillation (KD) process of multilingual NMT models. OpusDistillery's main features are the integration of openly available teacher models from OPUS-MT and Hugging Face, comprehensive multilingual support and robust GPU utilization tracking. We describe the tool in detail and discuss the individual contributions of its pipeline components, demonstrating its flexibility for different use cases. OpusDistillery is open-source and released under a permissive license, aiming to facilitate further research and development in the field of multilingual KD for any sequence-to-sequence task. Our code is available at https://github.com/Helsinki-NLP/OpusDistillery.