Lost in Variation : An Unsupervised Methodology for Mining Lexico-syntactic Patterns in Middle Arabic Texts
Year: 2025
Type: conference-paper
Abstract: Although Modern Standard Arabic and some dialects of Arabic have been extensively studied in NLP, Middle Arabic is still very much unknown to the field. However, Middle Arabic presents challenges not addressed by current NLP tools. In particular, it is characterized by variation since it mixes standard features, colloquial ones, as well as features that belong to neither of the two. Here, we introduce a methodology to identify, extract and classify variations of 13 manually retrieved formulas. These formulas come from the nine first booklets of SĪRAT AL-MALIK AL-ZĀHIR BAYBARS, a corpus of Damascene popular literature written in Middle Arabic and composed of 53,843 sentences. In total, we classified 20,386 sequences according to their similarity with the original formulas on multiple linguistic layers. We noticed that the variations in these formulas occur in a lexical, morphological and graphical level, but in opposition, the semantic and syntactic levels remain strictly invariable.
Source: HAL
Authors: Bezançon, Julien, Karam, Rimane, Lejeune, Gaël
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Agence Nationale de la Recherche
OpenAlex ID: W7120642943