Samsung R&D Institute Philippines @ WMT 2024 Low-resource Languages of Spain Shared Task

Dan John Velasco, Manuel Antonio Rufino, Jan Christian Blaise Cruz


Abstract
This paper details the submission of Samsung R&D Institute Philippines (SRPH) Language Intelligence Team (LIT) to the WMT 2024 Low-resource Languages of Spain shared task. We trained translation models for Spanish to Aragonese, Spanish to Aranese/Occitan, and Spanish to Asturian using a standard sequence-to-sequence Transformer architecture, augmenting it with a noisy-channel reranking strategy to select better outputs during decoding. For Spanish to Asturian translation, our method reaches comparable BLEU scores to a strong commercial baseline translation system using only constrained data, backtranslations, noisy channel reranking, and a shared vocabulary spanning all four languages.
Anthology ID:
2024.wmt-1.86
Volume:
Proceedings of the Ninth Conference on Machine Translation
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:
WMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
892–900
Language:
URL:
https://aclanthology.org/2024.wmt-1.86
DOI:
Bibkey:
Cite (ACL):
Dan John Velasco, Manuel Antonio Rufino, and Jan Christian Blaise Cruz. 2024. Samsung R&D Institute Philippines @ WMT 2024 Low-resource Languages of Spain Shared Task. In Proceedings of the Ninth Conference on Machine Translation, pages 892–900, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Samsung R&D Institute Philippines @ WMT 2024 Low-resource Languages of Spain Shared Task (Velasco et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.86.pdf