arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.03711cs.CL

NBF 在 SemEval-2025 任务 5:用于多语言学科推荐的 Light-Burst 注意力增强系统

NBF at SemEval-2025 Task 5: Light-Burst Attention Enhanced System for Multilingual Subject Recommendation

First Author Affiliation(第一作者机构)

Baharul Islam, Nasim Ahmad, Ferdous Ahmed Barbhuiya, Kuntal Dey

AI总结:

本文提出 Light-Burst 注意力增强系统,利用双语数据、负采样和低内部维度的维度即 token 自注意力机制,在 SemEval-2025 任务 5 的英德跨语言学科分类中以极少 GPU 资源取得有竞争力的召回率。

摘要:

我们介绍了提交给 SemEval 2025 任务 5 的系统,该任务聚焦于英语和德语学术领域中的跨语言学科分类。我们的方法在训练阶段利用双语数据,采用负采样和基于间隔的检索目标。我们证明了一种以维度作为 token 的自注意力机制,其设计显著降低了内部维度,能够有效编码用于学科检索的句子嵌入。在定量评估中,我们的系统在一般定量设置(所有学科)下取得了 32.24% 的平均召回率,在一般定性评估方法中分别取得了 43.16% 和 31.53% 的成绩,同时仅使用极少的 GPU 资源,凸显了其具有竞争力的性能。我们的结果表明,该方法能够在资源受限的条件下有效捕获相关学科信息,尽管仍有改进空间。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑