arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12937cs.CLcs.LG
收藏

课程学习与伪标签提升多标签阿拉伯方言识别模型的泛化能力

Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models

Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Ali Mekky, Mohamed El Zeftawy, Lara Hassan, Amr Keleg, Preslav Nakov

AI总结:

本研究通过课程学习和伪标签方法构建多标签阿拉伯方言识别数据集,并训练BERT模型提升泛化能力,最终在排行榜上取得宏平均F1值0.69的优异成绩。

摘要:

长期以来,阿拉伯方言识别(ADI)被建模为单标签分类任务,但近期研究认为应将其框架为多标签分类任务。然而,ADI仍受制于单标签数据集的可用性,目前没有大规模多标签资源可供训练。通过分析基于单标签ADI数据训练的模型,我们发现将此类数据集重新用于多标签阿拉伯方言识别(MLADI)的主要困难在于负样本的选择,因为许多被当作负样本的句子在多个方言中可能是可接受的。为了解决这些问题,我们通过使用GPT-4o生成自动多标签注释,并结合阿拉伯方言程度(ALDi)进行聚合,构建了一个多标签数据集。随后,我们使用课程学习策略训练了一个基于BERT的多标签分类器,该策略与方言复杂性和标签数量相匹配。在MLADI排行榜上,我们的最佳模型LAHJATBERT在宏平均F1值上达到0.69,相比之前最强的系统0.55有所提升。代码和数据可在https://mohamedalaa9.github.io/lahjatbert/获取。

英文摘要:

Being modeled as a single-label classification task for a long time, recent work has argued that Arabic Dialect Identification (ADI) should be framed as a multi-label classification task. However, ADI remains constrained by the availability of single-label datasets, with no large-scale multi-label resources available for training. By analyzing models trained on single-label ADI data, we show that the main difficulty in repurposing such datasets for Multi-Label Arabic Dialect Identification (MLADI) lies in the selection of negative samples, as many sentences treated as negative could be acceptable in multiple dialects. To address these issues, we construct a multi-label dataset by generating automatic multi-label annotations using GPT-4o and binary dialect acceptability classifiers, with aggregation guided by the Arabic Level of Dialectness (ALDi). Afterward, we train a BERT-based multi-label classifier using curriculum learning strategies aligned with dialectal complexity and label cardinality. On the MLADI leaderboard, our best-performing LAHJATBERT model achieves a macro F1 of 0.69, compared to 0.55 for the strongest previously reported system. Code and data are available at https://mohamedalaa9.github.io/lahjatbert/.

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。

↑