TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification

arXiv:2609.29633 · cs.CL, cs.AI, cs.LG · Submitted 2026-09-24 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-09-24

Updated: 2026-09-24

Comments: Accepted at ArabicNLP 2026, shared task AlexandriaX-2026

Project page: https://wmt-qe-task.github.io/wmt-qe-2023/subtasks/task2

License: http://creativecommons.org/licenses/by/4.0/

The gist: We present TTLab's submission to the AlexandriaX-2026 Subtask 3 on Arabic MT error span detection and classification.

Terminology

Abstract

We present TTLab's submission to the AlexandriaX-2026 Subtask 3 on Arabic MT error span detection and classification. Our system frames the task as token-level classification over surface forms, preserving character offsets to ensure exact alignment with the evaluation metric. To handle severe label imbalance, we employ a focal loss with class weighting and dialect-specific decoding thresholds. Among six Arabic pre-trained encoders, MARBERTv2 achieves the best overall performance of 40.8 and 40.91 on the development and test set, respectively, ranking out of all participating teams. While our system localizes error spans effectively, classification of rare error types remains challenging, highlighting the need for data augmentation for tail categories. The code is available at TTLab at AlexandriaX-2026

Sources

Related papers