Salam Khalifa · page 2

28 papers in our library · 2015–2026 · page 2 of 2

Papers

The most cited first (OpenAlex and our library).

Computational Benchmarks for Egyptian Arabic Child Directed Speech (2026)
ARABABYTALK-EGY makes Arabic child-adult interaction data usable for NLP. The Egyptian Arabic CHILDES corpus (EGYCHILDES) existed only as near-phonemic IPA transcriptions. Arabic NLP tools need orthographic input, so the corpus could not be used even for basic processing. The authors enriched it with three layers…
Learning Stress in Arabic Low-Resource Settings (2026)
The paper addresses automatic prediction of lexical stress in spoken Arabic varieties, which have far fewer resources than Modern Standard Arabic.
YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models (2026)
YallaMorph is a benchmark of over 600,000 test instances for controlled Arabic morphological generation. The task gives a lemma, a part of speech, a gloss and a feature bundle, and the model must produce the surface form, or say that the configuration is invalid. Items cover verbs (active and passive, perfective and…