Open in app

Sign In

Write

Sign In

Abdessalem Boukil
Abdessalem Boukil

7 Followers

Home

About

Published in Towards Data Science

·Jun 25, 2021

Comparing Facebook’s M2M to mT5 in low resources translation (English-Yoruba).

Looking for the best model for fine-tuning the translation tasks using rare language pairs. — TLDR; M2M performed really better than mT5. Inspiration Two months ago, I started working on Neural Machine Translation (NMT) for low-resource languages Zindi competition. The challenge is to train an NMT model with the highest ROUGE score using a rare language pair: Yoruba to English. Yoruba is a language spoken in…

NLP

8 min read

Comparing Facebook’s M2M to mT5 in low resources translation (English-Yoruba).
Comparing Facebook’s M2M to mT5 in low resources translation (English-Yoruba).
NLP

8 min read

Abdessalem Boukil

Abdessalem Boukil

7 Followers

Machine learning freelancer / Zindi & Kaggle Competitor

Following
  • Michael Galarnyk

    Michael Galarnyk

  • Kevin Shen

    Kevin Shen

  • Karim Bouazra

    Karim Bouazra

  • Skander Hannachi, Ph.D

    Skander Hannachi, Ph.D

  • Raj Sakthi

    Raj Sakthi

See all (11)

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech