Language Models

Robust Neural Machine Translation of User-Generated Content
PhD Defence
Jun 18, 2025 2:00 PM — 5:00 PM Centre Inria de Paris
Lydia Nishimwe
Robust Neural Machine Translation of User-Generated Content
Your Fairseq-trained model might have more embedding parameters than it should.
How a bug in reading SentencePiece vocabulary files causes some Fairseq-trained models to have up to 3k extra parameters in the embedding layer.
Lydia Nishimwe, posted on Mar 16, 2024
Last updated on Mar 22, 2025
Your Fairseq-trained model might have more embedding parameters than it should.
Normalisation lexicale de contenus générés par les utilisateurs sur les réseaux sociaux
🏆 Prix du Meilleur Article (Best Paper Award) - RÉCITAL 2023 🏆
Lydia Nishimwe
Normalisation lexicale de contenus générés par les utilisateurs sur les réseaux sociaux