Younes Samih · page 2
Papers
- From Multiple-Choice to Extractive QA: A Case Study for English and Arabic (2025 · 1 citation)
Annotated data for task-specific NLP is scarce outside a few major languages. The authors ask whether a dataset built for one QA format can be turned into another. They take part of BELEBELE, a multiple-choice reading-comprehension benchmark covering 122 language variants, and convert it into extractive QA (EQA)… - Conversion of Procedural Morphologies to Finite-State Morphologies: A Case Study of Arabic (2012 · 1 citation)
The Buckwalter Arabic Morphological Analyzer is a Perl program that splits a word into prefix, stem and suffix, checks the pieces against three lexicons and three co-occurrence tables, and retries with spelling variants when lookup fails. - EDRAC: Benchmarking Arabic Dialect Reading Comprehension (2026)
Dialectal Arabic has far fewer resources than Modern Standard Arabic. Existing dialect reading-comprehension tests are almost all multiple-choice and built from translated or social-media text. EDRAC fills this gap with an open-ended, generative QA benchmark for five dialects: Egyptian, Moroccan, Emirati, Syrian and… - Automatic Expansion and Retargeting of Arabic Offensive Language Training (2021)
The paper tackles a gap in Arabic offensive-language detection. Generic classifiers often miss abuse aimed at a particular entity, because such abuse can rely on deliberately twisted spellings of the target's name or on ordinary words used with hostile intent. The authors propose growing the training data…
This page in Markdown → https://md.research.elamur.ai/free/en/authors/younes-samih/page/2/