HW-TSC’s Submissions to the WMT 2025 Segment-level Quality Score Prediction Task

AbstractThis paper presents the submissions of Huawei Translate Services Center (HW-TSC) to the WMT 2025 Segment-level quality score prediction Task. We participate in 16 language pairs. For the prediction of translation quality scores for long multi-sentence text units, we propose an automatic evaluation framework based on alignment algorithms. Our approach integrates sentence segmentation tools and dynamic programming to construct sentence-level alignments between source and translated texts, then adapts sentence-level evaluation models to document-level assessment via sliding-window aggregation. Our submissions achieved competitive results in the final evaluations of all language pairs we participated in.