AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages

This paper introduces AfriMTE, human translation-evaluation data with simplified annotation guidelines for 13 African languages, and AfriCOMET, a learned machine translation quality metric built on an African-centric multilingual encoder. It addresses the difficulty of measuring translation progress for under-resourced African languages and reports improved correlation with human judgment over existing metrics.

Category

Research

Pricing

Free / open

Country

🌍 Pan-African

Last verified

10 Oct 2026

{
  "name": "AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages",
  "slug": "afrimte-and-africomet-enhancing-comet-to-embrace-under-resourced-african-languages",
  "category": "RESEARCH",
  "country": "Pan-African",
  "docs_status": "LIVE",
  "licensing_required": "NONE",
  "verified": true,
  "last_verified": "2026-10-10",
  "website": "https://arxiv.org/abs/2311.09828",
  "documentation_url": null
}