SSA-COMET: Do LLMs Outperform Learned Metrics in Evaluating MT for Under-Resourced African Languages?
This addresses the problem of poor MT evaluation for under-resourced African languages, offering an incremental improvement over existing metrics.
The paper tackled the challenge of evaluating machine translation quality for under-resourced African languages by introducing SSA-COMET metrics and a large-scale dataset, showing that SSA-COMET outperforms AfriCOMET and is competitive with Gemini 2.5 Pro, especially on languages like Twi, Luo, and Yoruba.
Evaluating machine translation (MT) quality for under-resourced African languages remains a significant challenge, as existing metrics often suffer from limited language coverage and poor performance in low-resource settings. While recent efforts, such as AfriCOMET, have addressed some of the issues, they are still constrained by small evaluation sets, a lack of publicly available training data tailored to African languages, and inconsistent performance in extremely low-resource scenarios. In this work, we introduce SSA-MTE, a large-scale human-annotated MT evaluation (MTE) dataset covering 14 African language pairs from the News domain, with over 73,000 sentence-level annotations from a diverse set of MT systems. Based on this data, we develop SSA-COMET and SSA-COMET-QE, improved reference-based and reference-free evaluation metrics. We also benchmark prompting-based approaches using state-of-the-art LLMs like GPT-4o, Claude-3.7 and Gemini 2.5 Pro. Our experimental results show that SSA-COMET models significantly outperform AfriCOMET and are competitive with the strongest LLM Gemini 2.5 Pro evaluated in our study, particularly on low-resource languages such as Twi, Luo, and Yoruba. All resources are released under open licenses to support future research.