Efforts to enhance sentence embeddings for better handling of informal language.
― 5 min read
Benoît Sagot
mOSCAR provides a multilingual dataset for improved AI understanding of text and images.
― 6 min read
ZeroMMT uses monolingual multimodal data to enhance translation without expensive datasets.
― 5 min read
Research on better translating low-resource languages using example selection techniques.
― 6 min read
A new corpus sheds light on the evolution of French-based Creole languages.
― 13 min read
New models CamemBERTav2 and CamemBERTv2 improve French language processing.
― 5 min read