Expanding FLORES+ Benchmark for more Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation
This work addresses the problem of evaluating machine translation for low-resource languages like Emakhuwa, but it is incremental as it extends an existing benchmark.
The paper tackled the lack of evaluation data for low-resource machine translation by expanding the FLORES+ benchmark to include Portuguese-Emakhuwa, resulting in publicly available datasets with baseline models that underperformed, highlighting challenges like spelling inconsistencies.
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.