English

Improving Similar Language Translation With Transfer Learning

Artificial Intelligence 2021-10-08 v3 Computation and Language

Abstract

We investigate transfer learning based on pre-trained neural machine translation models to translate between (low-resource) similar languages. This work is part of our contribution to the WMT 2021 Similar Languages Translation Shared Task where we submitted models for different language pairs, including French-Bambara, Spanish-Catalan, and Spanish-Portuguese in both directions. Our models for Catalan-Spanish (82.7982.79 BLEU) and Portuguese-Spanish (87.1187.11 BLEU) rank top 1 in the official shared task evaluation, and we are the only team to submit models for the French-Bambara pairs.

Keywords

Cite

@article{arxiv.2108.03533,
  title  = {Improving Similar Language Translation With Transfer Learning},
  author = {Ife Adebara and Muhammad Abdul-Mageed},
  journal= {arXiv preprint arXiv:2108.03533},
  year   = {2021}
}

Comments

Submitted to WMT 2021 Similar Language Task

R2 v1 2026-06-24T04:54:59.184Z