Mariano Felice

I am a research associate in the Natural Language and Information Processing group (Computer Laboratory, University of Cambridge), where I work as a member of the ALTA Institute. My research focuses on natural language processing for language learning and assessment, including automated content/test generation and grammatical error correction. I am also interested in evaluation methods.

During my PhD at Cambridge, I worked on grammatical error detection and correction for learners of English as a second language. My thesis focused on generating artificial errors to augment error-annotated corpora and improving evaluation methods. I was supervised by Prof. Ted Briscoe.

Before that, I completed an Erasmus Mundus International Masters in Natural Language Processing and Human Language Technologies, earning individual degrees from Universitat Autònoma de Barcelona (Spain) and the University of Wolverhampton (UK). My master's thesis explored the use of linguistic information for estimating the quality of machine translations and was primarily supervised by Prof. Lucia Specia.

I have a first degree in Information Systems from Universidad Nacional de Luján (Argentina) and an equivalent engineering degree in Spain.


I was one of the organisers of the BEA-2019 Shared Task on Grammatical Error Correction.


Awards and distinctions

2014 Winning system (1st place on the original test set) in the CoNLL 2014 Shared Task on Grammatical Error Correction. [results]
2013 Cambridge ESOL Studentship for PhD studies at the University of Cambridge.
2012 Honorable Mention (2nd Place) for master's thesis. MAVIR Awards 2012, Madrid, Spain.
2012 Best Student Award 2010-2012. Erasmus Mundus IM in NLP & HLT.
2010 Erasmus Mundus Scholarship.
2009 Honours diploma. Universidad Nacional de Luján, Argentina.


Contact details

Computer Laboratory
University of Cambridge
William Gates Building
15 JJ Thomson Avenue
Cambridge CB3 0FD, UK
+44 (0)1223 763727