We present our system submission for SemEval 2025 Task 5, which focuses on cross-lingual subject classification in the English and German academic domains. Our approach leverages bilingual data during training, employing negative sampling and a margin-based retrieval objective. We demonstrate that a dimension-as-token self-attention mechanism designed with significantly reduced internal dimensions can effectively encode sentence embeddings for subject retrieval. In quantitative evaluation, our system achieved an average recall rate of 32.24% in the general quantitative setting (all subjects), 43.16% and 31.53% of the general qualitative evaluation methods with minimal GPU usage, highlighting their competitive performance. Our results demonstrate that our approach is effective in capturing relevant subject information under resource constraints, although there is still room for improvement.
View on arXiv@article{islam2025_2505.03711,
title={ NBF at SemEval-2025 Task 5: Light-Burst Attention Enhanced System for Multilingual Subject Recommendation },
author={ Baharul Islam and Nasim Ahmad and Ferdous Ahmed Barbhuiya and Kuntal Dey },
journal={arXiv preprint arXiv:2505.03711},
year={ 2025 }
}