Machine Translation

Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation
A controlled pretraining study showing when and how data contamination inflates LLM evaluation scores.
Muhammed Yusuf Kocyigit, Eleftheria Briakou, Daniel Deutsch, Jiaming Luo, Colin Cherry, Markus Freitag
Better Quality Estimation for Low Resource Corpus Mining
Robust quality estimation models that make low-resource parallel corpus mining practical.
Muhammed Yusuf Kocyigit, Jiho Lee, Derry Tanti Wijaya
NUBIA: NeUral Based Interchangeability Assessor for Text Generation
A modular learned metric for evaluating the quality and semantic interchangeability of generated text.
Hassan Kane, Muhammed Yusuf Kocyigit, Ali Abdalla, Pelkins Ajanoh, Mohamed Coulibali