Dr Mariano Felice, Senior Researcher: Data Scientist for Language Assessment & Learning

Mariano's work involves looking at how artificial intelligence (AI) and natural language processing (NLP) can be used to improve computer-assisted learning and testing, from curating datasets and building models to supporting colleagues in the adoption of new technology. Mariano is also a Visiting Researcher at the University of Cambridge, where he was a Research Associate as part of the ALTA Institute before joining the ARG group at the British Council. He has a PhD in computer science from the University of Cambridge and has worked extensively on NLP for language learning and assessment, including grammatical error correction, automatic error typing, system evaluation, automated cloze test generation and item calibration. Mariano has published many scientific papers in top-tier NLP conferences, given talks and tutorials in different venues around the world and is a regular reviewer for workshops, journals and conferences in his field.


Watch Mariano's contribution to the panel discussion "Humans and technology" at the 2022 British Council New Directions conference in Denpasar, Indonesia, below:

Areas of expertise

  • Artificial Intelligence
  • Natural Language Processing
  • Automated Language Teaching and Assessment


Felice, M., Taslimipoor, S., Andersen, Ø. E., & Buttery, P. (2022). CEPOC: The Cambridge Exams Publishing Open Cloze dataset. In N. Calzolari, F. Béchet, P. Blache, K. Choukri, C. Cieri, T. Declerck, S. Goggi, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, J. Odijk, & S. Piperidis (Eds.), Proceedings of the 13th Language Resources and Evaluation Conference (pp. 4285–4290). European Language Resources Association.

Felice, M., Taslimipoor, S., & Buttery, P. (2022). Constructing open cloze tests using generation and discrimination capabilities of transformers. In S. Muresan, & P.  Nakov, & A. Villavicencio (Eds.), Findings of the Association for Computational Linguistics: ACL 2022 (pp. 1263–1273). Association for Computational Linguistics.

Felice, M., & Buttery, P. (2019). Entropy as a proxy for gap complexity in open cloze tests. In R. Mitkov, & G. Angelova (Eds.), Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019) (pp. 323–327). INCOMA Ltd.  

Bryant, C., Felice, M., Andersen, Ø. E., & Briscoe, T. (2019). The BEA-2019 shared task on grammatical error correction. In H. Yannakoudakis, E. Kochmar, C. Leacock, N. Madnani, I. Pilán, & T. Zesch (Eds.), Proceedings of The 14th Workshop on Innovative Use of NLP for Building Educational Applications (pp. 52–75). Association for Computational Linguistics.

Rei, M., Felice, M., Yuan, Z., & Briscoe, T. (2017). Artificial Error Generation with Machine Translation and Syntactic Patterns. In J. Tetreault, J. Burstein, C. Leacock, & H. Yannakoudakis (Eds.), Proceedings of the 12th workshop on innovative use of NLP for building educational applications (pp. 287–292). Association for Computational Linguistics.

Bryant, C., Felice, M., & Briscoe, T. (2017). Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction. In R. Barzilay, & M. Kan (Eds.), Proceedings of the 55th annual meeting of the Association for Computational Linguistics (Volume 1: Long Papers), (pp. 793–805). Association for Computational Linguistics.


  • PhD, Computer Science, University of Cambridge, 2016.
  • Erasmus Mundus International Masters, Natural Language Processing and Human Language Technologies, University of Wolverhampton, 2012
  • Erasmus Mundus International Masters, Natural Language Processing and Human Language Technologies, Universitat Autònoma de Barcelona, 2011
  • BSc, Information Systems, Universidad Nacional de Luján, 2009