Mariano Felice

I am a Senior Researcher and Data Scientist for Language Assessment and Learning at the British Council, where I'm part of the Assessment Research Group. My work involves looking at how artificial intelligence (AI) and natural language processing (NLP) can be used to improve computer-mediated learning and testing, from mining datasets and building models to supporting colleagues in the adoption of new technology.

I am also a visiting researcher in the Natural Language and Information Processing group (Computer Laboratory, University of Cambridge), where I spent many years as a research associate for the ALTA Institute. My research interests are mainly in NLP for language learning and assessment, including automated content/test generation, item calibration, CEFR-level estimation and grammatical error correction. I am also interested in evaluation methods.

I also did my PhD at Cambridge, where 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.

Latest

07/2022: Started a new position as a Senior Researcher and Data Scientist at the British Council.
12/2020: I was one of the instructors of A Crash Course in Automatic Grammatical Error Correction at COLING 2020.
08/2019: I was one of the organisers of the BEA-2019 Shared Task on Grammatical Error Correction.

Publications

• Shiva Taslimipoor, Luca Benedetto, Mariano Felice and Paula Buttery. 2024. Distractor Generation Using Generative and Discriminative Capabilities of Transformer-based Models. In In Proceedings of the 2024 International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Turin, Italy, May. European Language Resources Association.
• Marcos Zampieri, Kai North, Tommi Jauhiainen, Mariano Felice, Neha Kumari, Nishant Nair and Yash Mahesh Bangera. 2024. Language Variety Identification with True Labels. In Proceedings of the 2024 International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Turin, Italy, May. European Language Resources Association.
• Mariano Felice, Shiva Taslimipoor, Øistein E. Andersen and Paula Buttery. 2022. CEPOC: The Cambridge Exams Publishing Open Cloze dataset. In Proceedings of the 2022 International Conference on Language Resources and Evaluation (LREC 2022), pp. 4285–4290, Marseille, France, June. European Language Resources Association. [pdf | bib]
• Mariano Felice, Shiva Taslimipoor and Paula Buttery. 2022. Constructing Open Cloze Tests Using Generation and Discrimination Capabilities of Transformers. In Findings of the Association for Computational Linguistics (ACL 2022), pp. 1263–1273, Dublin, Ireland, May. Association for Computational Linguistics. [pdf | bib]
• Roman Grundkiewicz, Christopher Bryant and Mariano Felice. 2020. A Crash Course in Automatic Grammatical Error Correction. In Proceedings of the 28th International Conference on Computational Linguistics: Tutorial Abstracts, pp. 33–38, Barcelona, Spain (Online). International Committee for Computational Linguistics. [video | repository | pdf | bib]
• Mariano Felice and Paula Buttery. 2019. Entropy as a proxy for gap complexity in open cloze tests. In Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP 2019), pp. 323–327, Varna, Bulgaria, September. INCOMA Ltd. [pdf | bib]
• Christopher Bryant, Mariano Felice, Øistein E. Andersen and Ted Briscoe. 2019. The BEA-2019 Shared Task on Grammatical Error Correction. In Proceedings of the 14th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-2019), pp. 52–75, Florence, Italy, August. Association for Computational Linguistics. [pdf | bib]
• Marek Rei, Mariano Felice, Zheng Yuan and Ted Briscoe. 2017. Artificial Error Generation with Machine Translation and Syntactic Patterns. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-2017), pp. 287–292, Copenhagen, Denmark, September. Association for Computational Linguistics. [pdf | bib]
• Christopher Bryant, Mariano Felice and Ted Briscoe. 2017. Automatic annotation and evaluation of error types for grammatical error correction. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 793–805, Vancouver, Canada, August. Association for Computational Linguistics. [pdf | bib | code]
• Mariano Felice, Christopher Bryant and Ted Briscoe. 2016. Automatic extraction of learner errors in ESL sentences using linguistically enhanced alignments. In Proceedings of the 26th International Conference on Computational Linguistics (COLING 2016), pp. 825-835, Osaka, Japan, December. Japanese Association for Natural Language Processing. [pdf | bib | code]
• Mariano Felice. 2016. Artificial error generation for translation-based grammatical error correction. Ph.D. thesis, UCAM-CL-TR-895. University of Cambridge, October. [pdf | bib]
• Christopher Bryant and Mariano Felice. 2016. Issues in preprocessing current datasets for grammatical error correction. Technical report, UCAM-CL-TR-894. University of Cambridge, September. [pdf | bib]
• Zheng Yuan, Ted Briscoe and Mariano Felice. 2016. Candidate re-ranking for SMT-based grammatical error correction. In Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2016), pp. 256-266, San Diego, CA, June. Association for Computational Linguistics. [pdf | bib]
• Mariano Felice and Ted Briscoe. 2015. Towards a standard evaluation method for grammatical error detection and correction. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2015), pp. 578-587, Denver, CO, May. Association for Computational Linguistics. [pdf | bib | code]
• Mariano Felice and Zheng Yuan. 2014. To err is human, to correct is divine. In XRDS: Crossroads, The ACM Magazine for Students, vol. 21 num. 1, pp. 22-27, New York, NY, October. ACM. [publisher's website | bib]
• Mariano Felice, Zheng Yuan, Øistein E. Andersen, Helen Yannakoudakis and Ekaterina Kochmar. 2014. Grammatical error correction using hybrid systems and type filtering. In Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL 2014): Shared Task, pp. 15-24, Baltimore, MD, June. Association for Computational Linguistics. [pdf | bib]
• Mariano Felice and Zheng Yuan. 2014. Generating artificial errors for grammatical error correction. In Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), pp. 116-126, Gothenburg, Sweden, April. Association for Computational Linguistics. [pdf | bib]
• Zheng Yuan and Mariano Felice. 2013. Constrained grammatical error correction using Statistical Machine Translation. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning (CoNLL 2013): Shared Task, pp. 52–61, Sofia, Bulgaria, August. Association for Computational Linguistics. [pdf | bib]
• Mariano Felice and Lucia Specia. 2013. Investigating the contribution of linguistic information to quality estimation. In Machine Translation, vol. 27 num. 3-4, pp. 193-212. Springer, The Netherlands. [publisher's website | bib]
• Mariano Felice. 2012. Linguistic Indicators for Quality Estimation of Machine Translations. BULAG, vol. 37 num. 1, pp. 23-42. Presses universitaires de Franche-Comté, France. [publisher's website | bib]
• Mariano Felice. 2012. Linguistic Indicators for Quality Estimation of Machine Translations. Master's thesis. University of Wolverhampton, UK. [pdf | bib]
• Mariano Felice and Lucia Specia. 2012. Linguistic features for Quality Estimation. In Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT 2012), pp. 96-103, Montreal, Canada, June. Association for Computational Linguistics. [pdf | bib]
• Mariano Felice, Fernando R. A. Bordignon, Gabriel H. Tolosa. 2009. Spanish Automatic Text Enrichment. In Actas del XV Congreso Argentino de Ciencias de la Computación (CACIC 2009), pp. 673-683, Jujuy, Argentina, October. Universidad Nacional de Jujuy. [pdf | bib]
• Mariano Felice, Fernando R. A. Bordignon, Gabriel H. Tolosa. 2007. Enriquecimiento de Textos en Español mediante Generación Automática de Hipertexto. In Actas del IX Workshop de Investigadores en Ciencias de la Computación (WICC 2007), pp. 680-685, Trelew, Argentina, May. Universidad Nacional de la Patagonia San Juan Bosco. [pdf | bib]

Awards and distinctions

Reviewing

• Conferences and workshops: AAAI 2020, ACL 2019-2022, BEA 2015-2022, COLING 2018, EMNLP 2020-2021, NAACL-HLT 2021, NLP-TEA 2015-2018, RANLP 2013-2021, *SEM 2019-2021.
• Journals: Language Resources and Evaluation (LREV) [Springer], Progress in Artificial Intelligence (PRAI) [Springer].

Contact details

© Mariano Felice. Last updated: March 2024.
This website uses cookies for statistical purposes. If you do not agree to the use of cookies, please leave this page.