Computer Laboratory

Youmna Farag

picture of Youmna Farag

I am a postdoctoral research associate in the Natural Language and Information Processing Group, at the University of Cambridge Computer Laboratory. My postdoc project focuses on building argumentative dialogue systems with the aim of fostering open-minded thinking.

Before this, I got my PhD degree in Computer Science from the same department and group in 2020. In my PhD, I focused on modeling discourse coherence using deep learning, specifically multi-task learning, applying my models in the pedagogical domain and developing frameworks to evaluate and further interpret coherence models.

Prior to my PhD, I completed the MPhil in Advanced Computer Science at the Computer Laboratory in Cambridge. I also obtained my BSc in Computer Science from the American University in Cairo, and worked as a Software Engineer at Emerge Technology (now Pixelogic Media), Cairo, Egypt.

I am interested in machine learning, natural language processing, dialogue systems and computational social science. Apart from my research, I love racket sports, traveling, singing and reading.

Publications

  • Opening up Minds with Argumentative Dialogues. Youmna Farag, Charlotte O Brand, Jacopo Amidei, Paul Piwek, Tom Stafford, Svetlana Stoyanchev and Andreas Vlachos. Findings of the Association for Computational Linguistics: EMNLP 2022. [pdf]
  • Neural approaches to discourse coherence: modeling, evaluation and application. Youmna Farag. PhD Thesis, Computer Laboratory, University of Cambridge, 2021. [pdf]
  • Analyzing Neural Discourse Coherence Models. Youmna Farag, Josef Valvoda, Helen Yannakoudakis and Ted Briscoe. Proceedings of the First Workshop on Computational Approaches to Discourse (CODI 2020). [pdf]
  • Multi-Task Learning for Coherence Modeling. Youmna Farag and Helen Yannakoudakis. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019). [pdf]
  • Neural Automated Essay Scoring and Coherence Modeling for Adversarially Crafted Input. Youmna Farag, Helen Yannakoudakis and Ted Briscoe. Proceedings of the 16th Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2018). [pdf]
  • An error-oriented approach to word embedding pre-training. Youmna Farag, Marek Rei and Ted Briscoe. Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2017). [pdf]
  • Convolutional Neural Networks for Automated Essay Assessment. Youmna Farag. MPhil Thesis, Computer Laboratory, University of Cambridge, 2016. [pdf]

Teaching

  • Supervisor for Database, 2021 and 2022.
  • Supervisor for Information Retrieval, 2017 and 2018.
  • Supervisor for Natural Language Processing, 2018.

Contact

Email: yf273@cl.cam.ac.uk
Department of Computer Science and Technology
University of Cambridge
15 JJ Thomson Avenue
Cambridge CB3 0FD

Last updated 17/04/2023