Lydia Nishimwe
Lydia Nishimwe
Home
Experience
Projects
Publications
Talks
Blog
Contact
Light
Dark
Automatic
Transformers
UGC Translation Eval Challenges
Using LLMs to highlight the challenges of evaluating the machine translation of user-generated content.
When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content
EAMT 2026
Lydia Nishimwe
,
Benoît Sagot
,
Rachel Bawden
Robust Neural Machine Translation of User-Generated Content
🎓 PhD Thesis 🎓
Lydia Nishimwe
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
Normalisation lexicale de contenus générés par les utilisateurs sur les réseaux sociaux
🏆 Prix du Meilleur Article (Best Paper Award) - RÉCITAL 2023 🏆
Lydia Nishimwe
Cite
×