Author

Sébastien Diarra

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2025

R2T: Rule-Encoded Loss Functions for Sequence Tagging in Low-Resource Languages

Rule-to-Tag (R2T), a framework that turns linguistic rules into the training signal for neural sequence taggers in low-resource languages, is introduced, a first instance of a broader paradigm the authors call principled learning (PrL): using explicit principles as a learning signal, rather than relying on example-base...

Mamadou K. Keita, Christopher Homan, Sébastien Diarra · 2 citations