Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Axiom at AlexandriaX-2026: Confidence-Thresholded Dialectal Encoder Fine-Tuning for MT Error Span Detection and Classification

AbstractThis paper describes the “Axiom” team’s submission to the AlexandriaX-2026 Shared Task, focusing on Subtask 3: MT Error Detection and Classification. We frame the task of predicting fine-grained error spans and their corresponding LQM categories as a joint token classification problem using a BIO tagging scheme. Evaluating multiple Arabic encoders, we find that dialect-specific pretraining significantly outperforms generative extraction baselines. To address severe label imbalance across error categories, we apply a square-root scaled inverse-frequency class-weighted loss. Furthermore, we introduce a confidence-thresholded decoding strategy at inference to reduce false-positive span over-prediction. Our final system achieved highly competitive performance, ranking 5th on the official leaderboard. We highlight that while overlap-based detection is robust, exact span matching remains a persistent challenge due to the non-standardized nature of dialectal Arabic orthography.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

More from EMNLP 2026

All EMNLP 2026 papers →