发表机构
Text Technology Lab (TTLab); Goethe University Frankfurt（文本技术实验室; 法兰克福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出STAR-Ar，一种基于BERT-BiLSTM-CRF的序列标注架构，用于阿拉伯语论证挖掘中的话语单元识别与分类，在Daleel 2026任务中取得F1 73.7的成绩。
AI 中文摘要
论证挖掘（AM）是一项关键的NLP任务，但在阿拉伯语中资源仍然严重不足。本文提出了STAR-Ar，一种用于论证话语检测与分类的BERT-BiLSTM-CRF架构，作为我们参与Daleel 2026（首届阿拉伯语论证挖掘共享任务）的系统。该任务要求在辩论和社论文本中识别并分类论证话语单元（ADUs）。我们通过使用BERT-BiLSTM-CRF架构将这两个目标联合建模为词级序列标注任务，该架构结合了上下文Transformer嵌入与结构转移约束，以支持准确的跨度检测。STAR-Ar在验证集上取得了72.69的F1分数，在测试集上取得了73.7的F1分数。我们的领域特定分析表明，仅在社论上训练的模型性能不如在辩论上训练的模型，我们将这种差异主要归因于社论数据集的规模较小。STAR-Ar的代码可在GitHub上获取：TTLab at Daleel 2026。
英文摘要
Argument Mining (AM) is a critical NLP task that remains significantly under-resourced in Arabic. This paper presents $\testtt{STAR-Ar}$, a BERT-BiLSTM-CRF architecture for argument discourse detection and classification, as our system for Daleel 2026, the inaugural Arabic argument mining shared task. The task requires the identification and classification of argumentative discourse units (ADUs) in debate and editorial texts.We jointly model these two objectives as a token-level sequence labeling task using a BERT-BiLSTM-CRF architecture that combines contextual transformer embeddings with structural transition constraints to support accurate span detection. $\testtt{STAR-Ar}$ achieves an F1-score of 72.69 on validation and 73.7 on test data. Our domain-specific analysis shows that models trained exclusively on editorials underperform those trained on debates, a disparity we primarily attribute to the smaller size of the editorial dataset. The code for $\testtt{STAR-Ar}$ is available at ${\href{https://github.com/ENTAILab/daleel_2026_Arabic-Argumentative-Discourse-Mining}{\faGithub~TTLab at Daleel 2026}}$
CommentsAccepted at ArabicNLP 2026 Daleel-2026 shared task
