No Text Needed: Forecasting MT Quality and Inequity from Fertility and Metadata

Abstract

We show that translation quality can be predicted with surprising accuracy without ever running the translation system itself. Using only a handful of features, token fertility ratios, token counts, and basic linguistic metadata (language family, script, and region), we can forecast ChrF scores for GPT-4o translations across 203 languages in the FLORES-200 benchmark. Gradient boosting models achieve favorable performance (R^2=0.66 for XXEnglish and R^2=0.72 for EnglishXX). Feature importance analyses reveal that typological factors dominate predictions into English, while fertility plays a larger role for translations into diverse target languages. These findings suggest that translation quality is shaped by both token-level fertility and broader linguistic typology, offering new insights for multilingual evaluation and quality estimation.

Reproductions