Katerina Margatina

Google Scholar
Semantic Scholar

I am a 3rd year Ph.D. student at the Computer Science department at the University of Sheffield (SheffieldNLP), working on natural language processing & machine learning. My two amazing supervisors are Nikos Aletras (main) and Loïc Barrault, and my work is funded by an Amazon Alexa Fellowship. My research focuses on active learning, data collection, evaluation & benchmarking, robustness and language modeling – but I’m fascinated by other topics as well!

Currently, I am an Applied Scientist Intern at Amazon Web Services (AWS) in NYC, working with the AI human language technology group.

Until very recently, I lived in beautiful Copenhagen, where I spent 8 months visiting the CoAStaL group. I have the pleasure of working with Anders Søgaard and the rest of the team on exciting projects on learning from disagreement, fairness and cross-cultural NLP.

In 2019, I was working as a Machine Learning Engineer at the awesome Greek startup DeepSea Technologies. Previously, I obtained my diploma on Electrical & Computer Engineering at the National Technical University of Athens (NTUA).


Jun 7, 2022 Invited talk at Bloomberg’s AI Group / in-person in NYC.
Apr 26, 2022 Happy to start my internship at AWS in NYC, working with Miguel Ballesteros, Shuai Wang, Yogarshi Vyas and the rest of the Amazon Comprehend team!
Apr 22, 2022 Invited talk at NLPhD Speaker Series @ Saarland University / remote. (slides)
Feb 24, 2022 2 papers accepted at ACL 2022 (main conf.)!
Feb 22, 2022 Our recent paper, CAL, was included in the latest blog post of OpenAI’s Lilian Weng on Active Learning (thread, blog).
Feb 14, 2022 Very excited to co-organise the First Workshop on Dynamic Adversarial Data Collection (DADC@NAACL 2022, Seattle) with an amazing group of people! Check the Call for Papers and the Call for Participation to our Shared Task!
Aug 26, 2021 2 papers accepted at EMNLP 2021 (main conf.)!
Jul 1, 2021 Officially moved to Copenhagen, ready to start my PhD research visit at CoAStaL!

selected publications

  1. ACL
    On the Importance of Effectively Adapting Pretrained Language Models for Active Learning
    Margatina, K., Barrault, L., and Aletras, N.
    In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) 2022
  2. ACL

    🌍 Theme 🌎

    Challenges and Strategies in Cross-Cultural NLP
    Hershcovich, D., Frank, S., Lent, H., Lhoneux, M., Abdou, M., Brandl, S., Bugliarello, E., Piqueras, L. Cabello, Chalkidis, I., Cui, R., Fierro, C., Margatina, K., Rust, P., and Søgaard, A.
    In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) 2022
  3. EMNLP

    ✨ Oral ✨

    Active Learning by Acquiring Contrastive Examples
    Margatina, K., Vernikos, G., Barrault, L., and Aletras, N.
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021