Skip to content

Author

Thierry Etchegoyhen

We have 4 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access 2026

Vicomtech@WMT 2026: Mask-based Pruning for Model Compression

We describe Vicomtech’s participation in the constrained track of the WMT 2026 Shared Task on Model Compression. We addressed all three translation directions of the task, namely Czech to German, English to Simplified Chinese, and English to Egyptian Arabic, using Gemma 3 12B IT as our base model. Our approach performs...

David Ponce, Thierry Etchegoyhen · 0 citations
Open access 2026

IREKIER: An Easy Read Corpus for Basque and Spanish

The IREKIER corpus, based on ER news in Basque and Spanish from the Irekia transparency portal of the Basque Government, is described, which is currently one of the largest publicly shared resource to support training and evaluation of ER text adaptation models in these two languages.

Jesus Calleja, Thierry Etchegoyhen · 1 citation
2026

Judging Instruction Responses in a Low-Resource Language: A Case Study on Basque

This work investigates the performance of various LLM-as-a-judge in a low-resource scenario, namely Basque, and evaluates its correlation with human judgements, and shows that state of the art models exhibit fairly poor correlations with humans and amongst themselves.

David Ponce, Harritxu Gete, Thierry Etchegoyhen et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.