Elamur Research⌕
☰
home / authors / Haithem Afli

Haithem Afli

Haithem Afli has 6 papers in our library, in 2019–2026, most of them on Semitic languages, Language models & pretraining, Machine translation; often with Shehenaz Hossain, Fouad Shammary, Abdessalam Bouchekif.

6 papers in our library · 2019–2026

OpenAlex · ORCID · Wikidata · h-index 11 · 95 works · 548 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 31 times in our library · 4 more in our library without a page yet · ⭐ Paper Stars ranking: #8326

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🔬Munster Technological UniversityCork · Ireland2018–2026 · 40 papersEmployment since 2018 · Lecturer, Computer Science Departmentcurrent🎓Dublin City UniversityDublin · Ireland2015–2024 · 12 papersEmployment since 2015 · Research Scientist, School of Computing🔬Cork Institute of TechnologyCork · Ireland2018–2021 · 7 papersEmployment since 2018🔬ADAPT - Centre for Digital Content TechnologyDublin · Ireland2019–2024 · 3 papers🔬Laboratoire d’Informatique de l’Université du MansLe Mans · France2010–2014 · 3 papers🎓Le Mans UniversitéLe Mans · France2012–2016 · 2 papers🎓Université Européenne de BretagneRennes · France2010–2015Education 2010–2014Employment 2010–2015🎓Université Nantes Angers Le MansNantes · France2010–2015Education 2010–2014 · PhD in Computer Science, Computer ScienceEmployment 2010–2015 · PhD and PostDoc, Computer Science🎓Université Grenoble AlpesSaint-Martin-d'Hères · France2009–2010Education 2009–2010
🏛️Université de Grenoble IIIGrenoble · France2009–2010Education 2009–2010 · Master in Computational Linguistics, Informatics

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Computer Science · 6 worksArtificial Intelligence · 6 worksArts and Humanities · 5 worksLanguage and Linguistics · 5 worksPolitical Science and International Relations · 1 workSocial Sciences · 1 workComputer Vision and Pattern Recognition · 1 workSignal Processing · 1 work

🧭 Topics 8Research subjects and languages the work is about.Semitic languages · 5 worksLanguage models & pretraining · 2 worksMultilingual & cross-lingual NLP · 1 workReasoning · 1 workEnglish · 1 workMachine translation · 1 workQuestion answering · 1 workSpeech & spoken language · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.TF-IDF · 1 work

 Works by year

2020s

20261 paper20253 papers20221 paper

2010s

20191 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Hierarchical Deep Learning for Arabic Dialect Identification (2019 · 20 citations)
    This workshop paper addresses fine-grained Arabic dialect identification in the MADAR shared task. Each sentence must be assigned to one of 26 classes: the dialects of 25 Arab cities plus Modern Standard Arabic (MSA). The authors compare two systems.
  2. TF-IDF or Transformers for Arabic Dialect Identification? ITFLOWS participation in the NADI 2022 Shared Task (2022 · 7 citations)
    The paper describes the ITFLOWS team's entry to NADI 2022 Subtask 1, which asks systems to label tweets with the country-level Arabic dialect they come from.
  3. ADAPT–MTU HAI at QIAS2025: Dual-Expert LLM Fine-Tuning and Constrained Decoding for Arabic Islamic Inheritance Reasoning (2025 · 2 citations)
    This paper presents a system entered in the QIAS 2025 shared task, specifically its first subtask. The task is Arabic multiple-choice questions on Islamic inheritance law, with six options (A–F) and one correct answer. Solving the cases means applying fixed fractional shares, exclusion (ḥajb), redistribution (radd)…
  4. Enhancing Dialectal Arabic Intent Detection through Cross-Dialect Multilingual Input Augmentation (2025 · 2 citations)
    Arabic intent detection is difficult because regional dialects differ widely in vocabulary, spelling and structure, and they borrow words from other languages.
  5. ADAPT–MTU HAI at IWSLT2026: Robust Cascaded Speech Translation for Bhojpuri–Hindi and Irish–English (2026 · 1 citation)
    This paper presents WhiNN-ST, the submission from ADAPT–MTU HAI to the IWSLT 2026 shared task on speech translation in low-resource settings.
  6. ADAPT–MTU HAI at PalmX 2025: Leveraging Full and Parameter-Efficient LLM Fine-Tuning for Arabic Cultural QA (2025 · 1 citation)
    The authors describe their PalmX 2025 entry, a shared task that tests whether LLMs handle Arabic cultural knowledge, posed as four-option multiple-choice questions in Modern Standard Arabic.

All works

10 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

  1. Human Evaluation of English — Irish Transformer-Based NMT ↗arXiv:2403.02366 · Information 2022, 13(7), 309 · no summary yetSeamus Lankford, Haithem Afli, Andy Way2022 · 26 citations
  2. Hierarchical Deep Learning for Arabic Dialect IdentificationArabic Natural Language Processing Workshop (WANLP)Gael de Francony, Victor Guichard, Praveen Joshi, et al.2019 · 20 citations
  3. Balancing Translation Quality and Sentiment Preservation (Non-archival Extended Abstract) ↗Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track) · no summary yetPintu Lohar, Haithem Afli, Andy Way2018 · 10 citations
  4. TF-IDF or Transformers for Arabic Dialect Identification? ITFLOWS participation in the NADI 2022 Shared TaskArabic Natural Language Processing Workshop (WANLP)Fouad Shammary, Yiyi Chen, Zsolt T Kardkovacs, et al.2022 · 7 citations
  5. PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs ↗Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetManuel Frank, Haithem Afli2026 · 2 citations
  6. ADAPT–MTU HAI at QIAS2025: Dual-Expert LLM Fine-Tuning and Constrained Decoding for Arabic Islamic Inheritance ReasoningArabic Natural Language Processing Conference (ArabicNLP)Shehenaz Hossain, Haithem Afli2025 · 2 citations
  7. Enhancing Dialectal Arabic Intent Detection through Cross-Dialect Multilingual Input AugmentationWorkshop on Arabic Corpus LinguisticsShehenaz Hossain, Fouad Shammary, Bahaulddin Shammary, et al.2025 · 2 citations
  8. ADAPT–MTU HAI at IWSLT2026: Robust Cascaded Speech Translation for Bhojpuri–Hindi and Irish–EnglishInternational Conference on Spoken Language Translation (IWSLT)Pournima Sonawane, Haithem Afli2026 · 1 citation
  9. ADAPT–MTU HAI at PalmX 2025: Leveraging Full and Parameter-Efficient LLM Fine-Tuning for Arabic Cultural QAArabic Natural Language Processing Conference (ArabicNLP)Shehenaz Hossain, Haithem Afli2025 · 1 citation
  10. Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluation ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetKeren Artiaga et al.2025

 Co-authors here

5 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 31 times (of the 149,439 papers whose bibliographies we read); 17 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/haithem-afli/