Expanding FLORES+ Benchmark for More Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2024

Autores

António Ali, FDM (Autor) Outra; Henrique Lopes Cardoso (Autor) FEUP; Silva, RS (Autor) Outra

Ata de Conferência Internacional

Título: Ninth Conference on Machine Translation: WMT 2024

Páginas: 579-592

9th Conference on Machine Translation

Miami, 2024

Indexação

Scopus - 1 Citação

Outras Informações

ID Authenticus: P-018-0DY

Abstract (EN): As part of the Open Language Data Initiative shared tasks, we have expanded the FLORES+ evaluation set to include Emakhuwa, a low-resource language widely spoken in Mozambique. We translated the dev and devtest sets from Portuguese into Emakhuwa, and we detail the translation process and quality assurance measures used. Our methodology involved various quality checks, including post-editing and adequacy assessments. The resulting datasets consist of multiple reference sentences for each source. We present baseline results from training a Neural Machine Translation system and fine-tuning existing multilingual translation models. Our findings suggest that spelling inconsistencies remain a challenge in Emakhuwa. Additionally, the baseline models underperformed on this evaluation set, underscoring the necessity for further research to enhance machine translation quality for Emakhuwa. The data is publicly available at https://huggingface.co/datasets/LIACC/Emakhuwa-FLORES ©2024 Association for Computational Linguistics.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 13