| title | Model-Based Quality Assessment for Massively Multilingual Parallel Data |
|---|---|
| authors | Abdelaziz M. A. Ibrahim, Zihao Li, Jörg Tiedemann, Shaoxiong Ji |
| date | 2026-05-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.00285 |
| affiliation | MaLA-LM |
| links | abs pdf hf |
| abstract | Large-scale multilingual bitext often contains two distinct problems: non-parallel sentence pairs and low-quality translations. We decompose model-based assessment for such data into two independent components: parallelism assessment with multilingual embeddings and reference-free quality estimation (QE). For parallelism, we benchmark four embedding models on FLORES-200 and BOUQuET retrieval tasks, covering 6,654 source--target directions in our target language-pair inventory. For QE, we evaluate nine reference-free evaluators on professional FLORES-200 translations across 41,412 ordered source--target directions. Results show that no model is universally reliable across translation directions. Naive QE ensembles dilute strong model signals, while documented target-language coverage is strongly associated with higher QE scores. Overall, these findings suggest that multilingual parallel-data assessment is best approached as a direction-aware routing and calibration problem, where no single universal metric is expected to suffice across all languages. |
cite
@misc{ibrahim2026model,
title={Model-Based Quality Assessment for Massively Multilingual Parallel Data},
author={Abdelaziz M. A. Ibrahim and Zihao Li and Jörg Tiedemann and Shaoxiong Ji},
year={2026},
eprint={2606.00285},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.00285}
}