no code implementations • RANLP 2021 • Thierry Etchegoyhen, David Ponce, Harritxu Gete, Victor Ruiz
Adaptive Machine Translation purports to dynamically include user feedback to improve translation quality.
1 code implementation • LREC 2022 • Harritxu Gete, Thierry Etchegoyhen, David Ponce, Gorka Labaka, Nora Aranberri, Ander Corral, Xabier Saralegi, Igor Ellakuria, Maite Martin
Document-level Neural Machine Translation aims to increase the quality of neural translation models by taking into account contextual information.
no code implementations • 17 Jun 2024 • Jesús Calleja, Thierry Etchegoyhen, David Ponce
Easy Read text is one of the main forms of access to information for people with reading difficulties.
no code implementations • 18 Dec 2023 • David Ponce, Thierry Etchegoyhen, Jesús Calleja Pérez, Harritxu Gete
Our results provide a fine-grained analysis of the potential and limitations of large language models for SPRP, with significant improvements achievable using relatively small amounts of training data and model parameters overall, and remaining limitations for all models on the task.