arXiv cs.CL· Amr Keleg, Ahmed Amine Ben Abdallah, Taha Yassine, Chadi Helwe, Imane Guellil, Nedjma Ousidhoum·· 12 小时前AI 评分19
跨越方言的罗马化阿拉伯语：使用观点、习惯与语言变异
Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation
AI 导读
研究通过调研阿拉伯语使用者，考察阿尔及利亚、埃及、黎巴嫩、摩洛哥和突尼斯五种方言对拉丁字母书写阿拉伯语（Arabizi）的认知与使用，并发布两个资源：VARabiziLex 基于字符级对齐揭示方言内系统规律与方言间差异，VARabiziCues 为人工构建的阿拉伯文与多种 Arabizi 转写平行句料，用于测试说话者在句子层面识别这种风格变异的能力。
正文 · 原文
Abstract:Arabizi refers to Arabic written in Latin script. Although previous studies have shown that the prevalence and usage of Arabizi vary by factors such as region and age group, most NLP research on Arabic texts treats it as a temporary phenomenon resulting from limited technological support for the Arabic script. In this work, we engage with Arabic speakers to collect insights on their perceptions and usage of Arabizi. We further examine writing norms among speakers of different dialects, focusing on Algerian, Egyptian, Lebanese, Moroccan, and Tunisian Arabic. To this end, we release two resources. First, we perform a character-level alignment of Arabic words to study inter- and intradialectal variation across these five dialects, based on words transliterated by the surveyed participants (VARabiziLex), finding systematic intradialectal regularity and interdialectal variation. Second, to study Arabic speakers' ability to identify this stylistic variation at the sentence level, we build VARabiziCues, a manually curated parallel corpus of sentences written in Arabic script alongside multiple Arabizi transliterations, collected from speakers of the same five dialects. Our study presents the largest human-centered, cross-dialectal study of Arabizi perceptions and practices to date.
| Comments: | EMNLP 2026 (Findings). Kindly refer to the official version, as the arXiv version's formatting is suboptimal |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.02555 [cs.CL] |
| (or arXiv:2608.02555v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.02555 arXiv-issued DOI via DataCite |
Submission history
From: Amr Keleg [view email]
[v1]
Mon, 3 Aug 2026 17:39:45 UTC (1,212 KB)
[v2]
Fri, 23 Oct 2026 09:10:34 UTC (2,303 KB)
来源：arXiv cs.CL · arxiv.org