5 papers
Span-Level Machine Translation Meta-Evaluation
Stefano Perrella, Eric Morales Agostinho, Hugo Zaragoza
Machine Translation (MT) and automatic MT evaluation have improved dramatically in recent years, enabling numerous novel applications. Automatic evaluation techniques have evolved…
Estimating Machine Translation Difficulty
Lorenzo Proietti, Stefano Perrella, Vilém Zouhar +2
Machine translation quality has steadily improved over the years, achieving near-perfect translations in recent benchmarks. These high-quality outputs make it difficult to distingu…
Preliminary Ranking of WMT25 General Machine Translation Systems
Tom Kocmi, Eleftherios Avramidis, Rachel Bawden +25
We present the preliminary rankings of machine translation (MT) systems submitted to the WMT25 General Machine Translation Shared Task, as determined by automatic evaluation metric…
Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progress
Lorenzo Proietti, Stefano Perrella, Roberto Navigli
In Machine Translation (MT) evaluation, metric performance is assessed based on agreement with human judgments. In recent years, automatic metrics have demonstrated increasingly hi…
Beyond Correlation: Interpretable Evaluation of Machine Translation Metrics
Stefano Perrella, Lorenzo Proietti, Pere-LluÃs Huguet Cabot +2
Machine Translation (MT) evaluation metrics assess translation quality automatically. Recently, researchers have employed MT metrics for various new use cases, such as data filteri…