Amr Keleg


The university of Edinburgh

Edinburgh, Scotland

Hello (أهلًا وسهلًا)! 👋👋

My name is Amr Keleg عمرو قلج (/ʕamr/ /kɯˈɫɯtʃ/). I am a PhD student (CDT in NLP) at the University of Edinburgh, working under the supervison of Walid Magdy and Sharon Goldwater. I am currently studying the variation across and between the Arabic dialects, their mutual intelligibility, and the implications of this variation on the creation of multi-dialect Arabic datasets.

Additionally, I am interested in Arabizi (the romanized form of Arabic). I developed a rule-based tool transliterating Arabizi into Arabic script. Ping me if you are interested in sharing ideas related to Arabizi (idenitifcaiton/transliteartion/…), and/or collaborating on that!

Multilinguality is another field/cause that I am becoming more and more interested about!

Selected Publications

  1. ALDi: Quantifying the Arabic Level of Dialectness of Text
    Keleg, Amr, Goldwater, Sharon, and Magdy, Walid
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing 2023
  2. Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification
    Keleg, Amr, and Magdy, Walid
    In Proceedings of ArabicNLP 2023 2023
  3. DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models
    Keleg, Amr, and Magdy, Walid
    In Findings of the Association for Computational Linguistics: ACL 2023 2023
  4. SMASH at Qur’an QA 2022: Creating Better Faithful Data Splits for Low-resourced Question Answering Scenarios
    Keleg, Amr, and Magdy, Walid
    In Proceedings of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection 2022