--- title: "Kareem Darwish — papers, page 2 — Elamur Research" description: "Kareem Darwish, Hamad bin Khalifa University: 55 papers on Elamur Research (2002–2026), h-index 38 — affiliations, topics, co-authors…" canonical: "https://research.elamur.ai/free/en/authors/kareem-darwish/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/kareem-darwish/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Kareem Darwish](https://md.research.elamur.ai/free/en/authors/kareem-darwish/) / page 2 # Kareem Darwish · page 2 55 papers in our library · 2002–2026 · page 2 of 3 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/kareem-darwish/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/kareem-darwish/) [1](https://md.research.elamur.ai/free/en/authors/kareem-darwish/) **2** [3](https://md.research.elamur.ai/free/en/authors/kareem-darwish/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/kareem-darwish/page/3/) 26. **[Learning from Relatives: Unified Dialectal Arabic Segmentation](https://md.research.elamur.ai/free/en/papers/samih-2017-learning-relatives-unified-dialectal-arabic/)** *(2017 · 37 citations)* Social-media Arabic is mostly written in regional dialects. Earlier segmenters were built for one dialect at a time, so text first had to pass through dialect identification, which can be less than 90% accurate. The authors ask two questions: how well does a segmenter trained on one dialect handle the others, and can… 27. **[Using Stem-Templates to Improve Arabic POS and Gender/Number Tagging](https://md.research.elamur.ai/free/en/papers/darwish-2014-stem-templates-improve-arabic-pos/)** *(2014 · 37 citations)* The paper builds an end-to-end Arabic pipeline: correction of common spelling confusions (alef forms, ta marbuta and ha, alef maqsura and ya), character-level segmentation with a CRF, POS tagging with a CRF, and gender and number tagging for nouns and adjectives. 28. **[Simple Effective Microblog Named Entity Recognition: Arabic as an Example](https://md.research.elamur.ai/free/en/papers/darwish-2014-simple-effective-microblog-named-entity/)** *(2014 · 36 citations)* The paper addresses named entity recognition (NER) on Arabic tweets. Newswire-trained systems perform poorly on tweets because the language is informal and dialectal, spelling varies, entity names are often shortened, and Arabic has no capitalization cue. The authors build a CRF baseline with simple character-affix… 29. **[QCRI @ DSL 2016: Spoken Arabic Dialect Identification Using Textual Features](https://md.research.elamur.ai/free/en/papers/eldesouki-2016-qcri-dsl-2016-spoken-arabic/)** *(2016 · 32 citations)* This paper describes QCRI's system for the Arabic sub-task of the DSL 2016 shared task (VarDial3). The task is to assign an utterance to one of five varieties: Egyptian, Gulf, Levantine, North-African or MSA. The training data is unusual. It consists of roughly 7.6K ASR transcripts in Buckwalter transliteration that… 30. **[Arabic Diacritic Recovery Using a Feature-Rich biLSTM Model](https://md.research.elamur.ai/free/en/papers/darwish-2020-arabic-diacritic-recovery-using-feature/)** *(2020 · 29 citations)* Arabic is usually written without short vowels (diacritics), so readers must supply them to pronounce words and resolve meaning. 31. **[Part-of-Speech Tagging for Arabic Gulf Dialect Using Bi-LSTM](https://md.research.elamur.ai/free/en/papers/alharbi-2018-part-speech-tagging-arabic-gulf/)** *(2018 · 26 citations)* Standard Arabic taggers break down on dialectal social-media text, and Gulf Arabic had no dedicated tagger at all, although it is widely used online. 32. **[Automatic Correction of Arabic Text: a Cascaded Approach](https://md.research.elamur.ai/free/en/papers/mubarak-2014-automatic-correction-arabic-text-cascaded/)** *(2014 · 25 citations)* The paper describes QCRI's entry in the QALB-2014 shared task on automatically correcting Arabic text, using the QALB dataset. 33. **[Examining the Effect of Improved Context Sensitive Morphology on Arabic Information Retrieval](https://md.research.elamur.ai/free/en/papers/darwish-2005-examining-effect-improved-context-sensitive/)** *(2005 · 25 citations)* Arabic words carry many attached prefixes and suffixes, so retrieval systems must decide how to merge related word forms. 34. **[Arabic Cross-Document Person Name Normalization](https://md.research.elamur.ai/free/en/papers/magdy-2007-arabic-cross-document-person-name/)** *(2007 · 20 citations)* The paper addresses cross-document person-name normalization for Arabic news. The goal is to decide which person entities, each already resolved inside its own document, refer to the same individual across documents. The task is hard for three reasons: transliterated foreign names have many spellings, common Arabic… 35. **[IslamicEval 2025: The First Shared Task of Capturing LLMs Hallucination in Islamic Content](https://md.research.elamur.ai/free/en/papers/mubarak-2025-islamiceval-2025-first-shared-task/)** *(2025 · 19 citations)* LLMs used for Arabic religious questions often misquote or invent Qur'anic verses and Hadiths. IslamicEval 2025 is the first shared task built around measuring and catching such errors. It has two parts. 36. **[Improving Arabic Text Categorization Using Transformer Training Diversification](https://md.research.elamur.ai/free/en/papers/chowdhury-2020-improving-arabic-text-categorization-transformer/)** *(2020 · 17 citations)* The paper asks how well Arabic short-text topic classifiers carry over when the training text and the test text differ in source, platform, or variety of Arabic (MSA vs. 37. **[A System for Diacritizing Four Varieties of Arabic](https://md.research.elamur.ai/free/en/papers/mubarak-2019-system-diacritizing-four-varieties-arabic/)** *(2019 · 17 citations)* Arabic is usually written without short vowels (diacritics). Readers must infer them to pronounce words, so automatic diacritic restoration matters for text-to-speech and language learning. This demo paper presents a deployed system that adds diacritics back for four varieties: Classical Arabic (CA), Modern Standard… 38. **[NatiQ: An End-to-end Text-to-Speech System for Arabic](https://md.research.elamur.ai/free/en/papers/abdelali-2022-natiq-end-end-text-speech/)** *(2022 · 16 citations)* The paper presents NatiQ, a web-deployed Arabic text-to-speech system. Arabic is a hard case for TTS because ordinary text leaves out short vowels, so the pronunciation has to be reconstructed before synthesis. The authors recorded two in-house corpora at 44kHz. "Amina" is an expressive female voice reading… 39. **[Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM](https://md.research.elamur.ai/free/en/papers/eldesouki-2017-arabic-multi-dialect-segmentation-bi/)** *(2017 · 16 citations)* The paper segments four Arabic dialects (Egyptian, Levantine, Gulf, Maghrebi) from raw Twitter text. Only about 350 manually segmented tweets per dialect are used for training, with 5-fold cross-validation and a 70/10/20 split. Two approaches are compared. An SVM ranker generates all segmentations of a word from a… 40. **[BALSAM: A Platform for Benchmarking Arabic Large Language Models](https://md.research.elamur.ai/free/en/papers/matham-2025-balsam-platform-benchmarking-arabic-large/)** *(2025 · 14 citations)* Arabic LLMs still lag behind English ones, and the gap is hard to measure. Most Arabic benchmarks use static public data and cover only a narrow set of capabilities. They also lack a hosted platform with hidden test sets, so training-data contamination is likely and progress is difficult to track. A large consortium… 41. **[Bert Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets](https://md.research.elamur.ai/free/en/papers/harrag-2020-bert-transformer-model-detecting-arabic/)** *(2020 · 14 citations)* The paper tackles a classification problem for Arabic social media: telling apart tweets written by people from "deepfake" text produced by a neural language model. 42. **[QC-GO Submission for MADAR Shared Task: Arabic Fine-Grained Dialect Identification](https://md.research.elamur.ai/free/en/papers/samih-2019-qc-go-submission-madar-shared/)** *(2019 · 13 citations)* The paper reports the QC-GO team's entry in the MADAR Shared Task on fine-grained Arabic dialect identification. 43. **[QCRI@QALB-2015 Shared Task: Correction of Arabic Text for Native and Non-Native Speakers' Errors](https://md.research.elamur.ai/free/en/papers/mubarak-2015-qcri-qalb-2015-shared-task/)** *(2015 · 12 citations)* The authors present the system QCRI entered in QALB-2015, a shared competition on automatically fixing errors in written Arabic. 44. **[Fanar 2.0: Arabic Generative AI Stack](https://md.research.elamur.ai/free/en/papers/team-2026-fanar-2-0-arabic-generative/)** *(2026 · 11 citations)* Fanar 2.0 is QCRI's second-generation Arabic-centric generative AI platform. It is built and run entirely in-house, with no external AI providers, on a modest budget of 256 H100 GPUs. Arabic is also scarce online, at roughly 0.5% of web text. Instead of scaling up, the team chose careful curation. They continued… 45. **[From RAG to Agentic RAG for Faithful Islamic Question Answering](https://md.research.elamur.ai/free/en/papers/bhatia-2026-rag-agentic-rag-faithful-islamic/)** *(2026 · 8 citations)* LLMs are increasingly used to answer Islamic questions, where an unsupported answer can have real religious consequences. 46. **[Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions](https://md.research.elamur.ai/free/en/papers/atif-2025-sacred-synthetic-evaluating-llm-reliability/)** *(2025 · 8 citations)* People increasingly ask chatbots about Islamic law, yet no benchmark had tested whether LLMs answer such questions correctly for a specific Sunni legal school (madhhab), or whether they decline when unsure. 47. **[Arabic Retrieval Revisited: Morphological Hole Filling](https://md.research.elamur.ai/free/en/papers/darwish-2012-arabic-retrieval-revisited-morphological-hole/)** *(2012 · 8 citations)* Arabic search engines depend on stemming. The strongest statistical stemmers still cannot merge singular nouns with their "broken" (internally changed) plurals. They also split named entities whose final letter shifts when a suffix is added. Darwish and Ali address this gap with a character-level transformation model… 48. **[Arabic Diacritization Using Morphologically Informed Character-Level Model](https://md.research.elamur.ai/free/en/papers/elmallah-2024-arabic-diacritization-morphologically-informed-character/)** *(2024 · 7 citations)* The paper restores Arabic short vowels with a character-level recurrent model, and adds the morpheme boundaries that a separate segmenter predicts. 49. **[Diacritization of Maghrebi Arabic Sub-Dialects](https://md.research.elamur.ai/free/en/papers/abdelali-2018-diacritization-maghrebi-arabic-sub-dialects/)** *(2018 · 6 citations)* Arabic is usually written without short vowels, and systems such as text-to-speech must restore them. Most diacritization research has targeted Modern Standard Arabic (MSA), so the authors address two Maghrebi sub-dialects, Moroccan (MOR) and Tunisian (TUN). Their data are two dialectal New Testament translations of… 50. **[Arabic Curriculum Analysis](https://md.research.elamur.ai/free/en/papers/mubarak-2020-arabic-curriculum-analysis/)** *(2020 · 5 citations)* Arabic has few NLP tools for checking whether school textbooks meet their learning goals, for example in the vocabulary they teach. [← prev](https://md.research.elamur.ai/free/en/authors/kareem-darwish/) [1](https://md.research.elamur.ai/free/en/authors/kareem-darwish/) **2** [3](https://md.research.elamur.ai/free/en/authors/kareem-darwish/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/kareem-darwish/page/3/)