Deep Learning

When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content
Preprint
Lydia Nishimwe, Benoît Sagot, Rachel Bawden
When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content
Robust Neural Machine Translation of User-Generated Content
🎓 PhD Thesis 🎓
Lydia Nishimwe
Robust Neural Machine Translation of User-Generated Content
Making Sentence Embeddings Robust to User-Generated Content
LREC-COLING 2024
Lydia Nishimwe, Benoît Sagot, Rachel Bawden
Making Sentence Embeddings Robust to 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 Jan 8, 2026
Your Fairseq-trained model might have more embedding parameters than it should.
Fairseq Bug Fix
A bug in reading SentencePiece vocabulary files causes models to have 3k extra params in the embedding layer.
Fairseq Bug Fix
RoLASER
Making LASER sentence embeddings robust to user-generated content via Knowledge Distillation and Data Augmentation.
RoLASER
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
Inria-ALMAnaCH at the WMT 2022 shared task: Does Transcription Help Cross-Script Machine Translation?
Jesujoba O Alabi, Lydia Nishimwe, Benjamin Muller, Camille Rey, Benoît Sagot, Rachel Bawden