Lydia Nishimwe
Lydia Nishimwe
Home
Experience
Projects
Publications
Talks
Blog
Contact
Light
Dark
Automatic
Projects
UGC Translation Eval Challenges
Using LLMs to highlight the challenges of evaluating the machine translation of user-generated content.
Fairseq Bug Fix
A bug in reading SentencePiece vocabulary files causes models to have 3k extra params in the embedding layer.
RoLASER
Making LASER sentence embeddings robust to user-generated content via Knowledge Distillation and Data Augmentation.
Cite
×