Multilingual & Culturally Aware AI
Language technologies — translation, speech and language models — that work across high- and low-resource languages and cultures.
Why it matters: Because most of the world's languages are under-served by current AI, widening rather than closing gaps.
Featured events
- Institutional Co-Lead, Rinn Artificial Intelligence at MTU — Research leadership, 2026
- IWSLT 2026 — robust cascaded speech translation (ADAPT–MTU HAI) — Shared-task publication, 2026
- adaptNMT & adaptMLLM — open-source multilingual MT tooling — Research software, 2023
- ArabicNLP 2025 — winning PalmX system for Arabic cultural QA — Shared-task publication, 2025
Related projects
Publications (44)
- ADAPT–MTU HAI at IWSLT2026: Robust Cascaded Speech Translation for Bhojpuri–Hindi and Irish–English — Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), 2026
- Enhancing Dialectal Arabic Intent Detection through Cross-Dialect Multilingual Input Augmentation — Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4), 2025
- Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluation — Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
- ADAPT–MTU HAI at QIAS2025: Dual-Expert LLM Fine-Tuning and Constrained Decoding for Arabic Islamic Inheritance Reasoning — Proceedings of the Third Arabic Natural Language Processing Conference: Shared Tasks, 2025
- ADAPT–MTU HAI at PalmX 2025: Leveraging Full and Parameter-Efficient LLM Fine-Tuning for Arabic Cultural QA — Proceedings of the Third Arabic Natural Language Processing Conference: Shared Tasks, 2025
- The Influence of Iconicity in Transfer Learning for Sign Language Recognition — Int. Conf. on Applications of Natural Language to Information Systems (NLDB), Springer, 2024
- Transformers for Low-Resource Languages: Is Féidir Linn! — arXiv preprint arXiv:2403.01985, 2024
- adaptNMT: An Open-Source, Language-Agnostic Development Environment for Neural Machine Translation — Language Resources and Evaluation, 57(4), 1671–1696, 2023
- adaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds — Information, 14(12), 638, 2023
- Design of an Open-Source Architecture for Neural Machine Translation — Proceedings of the 1st Workshop on Open Community-Driven Machine Translation, 2023
- A Decision-Level Approach to Multimodal Sentiment Analysis — Computational Linguistics and Intelligent Text Processing (CICLing 2018), Lecture Notes in Computer Science, 2023
- TF-IDF or Transformers for Arabic Dialect Identification? ITFLOWS participation in the NADI 2022 Shared Task — Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), 2022
All 44 publications in this theme →
Milestones
- 2010 — MA in Computational Linguistics, Université Grenoble Alpes
- 2014 — PhD in Computer Science (NLP), Le Mans Université
- 2016 — Multimodal comparable corpora for machine translation (Natural Language Engineering)
- 2019 — Arabic dialect identification & emotion detection (WANLP, SemEval-2019)
- 2022 — gaHealth — English–Irish bilingual health corpus (LREC 2022)
- 2023 — adaptNMT & adaptMLLM — open-source multilingual MT tooling
- 2025 — ArabicNLP 2025 — winning PalmX system for Arabic cultural QA
- 2026 — Institutional Co-Lead, Rinn Artificial Intelligence at MTU
- 2026 — IWSLT 2026 — robust cascaded speech translation (ADAPT–MTU HAI)
See the full research agenda · collections · research journey.