Euan McGill

Euan McGill

Linguist, data engineer, and NLP researcher · /ˌju.ən mə.ˈgɪl/

I’m a senior data manager at Cambridge University Press & Assessment, specifically within the Cambridge Dictionary team. I am also an active researcher in the academic community being an alumnus of the University of Edinburgh, and more recently receiving a doctorate in natural language processing (NLP) from Universitat Pompeu Fabra, Barcelona. My primary research interests centre around accessibility and low-resource NLP. My thesis and other works have aimed to tackle these challenges through machine translation, dataset creation, and other low-resource methods. I am also passionate about democracy and the (political) geography of Britain and beyond.

CV (PDF)   Google Scholar   ORCID   GitHub   LinkedIn

Updates

Attended EURALEX 2026 in Vienna on behalf of the Cambridge Dictionary.

I successfully defended my doctoral thesis “The Data Problem behind Sign Language Translation” and achieved the grade Cum Laude.

I began a two-year reviewership on the Computational Linguistics journal.

See all updates...

Projects

Proportional Representation for the UK

Proportional representation results for the 2024 general election

Modelling UK national and local elections using party-list proportional representation, both from the latest opinion polls (preview image above) and from historical elections.

Spoken language text-to-Sign Language video parallel datasets

Using a semi-automated pipeline to align audio and transcript text from parliamentary sessions to the video feed including Sign Language interpretation. The goal is to expand the amount of parallel data available for spoken/Sign Language pairs

BSL/English from Hansard and parliamentlive.tv: Paper (2023), data. LSC/Catalan from the Catalan parliament: Thesis (Chapter 9), data.

SignON

A EU Horizon 2020 project SignON, which aimed to develop a spoken-to-sign language translation platform accessible to all.

Photos from planes

Facing east over London from the air at night
Flying over Hyde Park, and looking south east over London at night.

A collection of photos I’ve taken over the years from plane windows.

More projects on GitHub

Publications

Machine translation

The Data Problem behind Sign Language Translation

McGill, E.

Doctoral thesis, Universitat Pompeu Fabra,

Linguistic Processing for Sign Language Translation

Saggion, H., McGill, E., Chiruzzo, L., & Egea Gómez, S.

In: Way, A., Leeson, L., & Shterionov, D. (eds.), Sign Language Machine Translation. Springer, . Book chapter.

TRIBBLE: TRanslating IBerian languages Based on Limited E-resources

Kuzmin, I., Przybyła, P., McGill, E. & Saggion, H.

Shared Task: Translation into Low-Resource Languages of Spain @ Ninth Conference on Machine Translation (WMT24), , pp. 955-959. Miami, Florida, USA.

Can True Zero-shot methods with Large Language Models be Adopted for Sign Language Translation?

McGill, E. & Saggion, H.

Proceedings of the First International Workshop on Knowledge-Enhanced Machine Translation (KEMT2024), , pp. 40-43. Sheffield, England.

Bootstrapping Pre-trained Word Embeddings for Sign Language Gloss Translation

McGill, E., Chiruzzo, L., & Saggion, H.

Proceedings of the 25th Annual Conference of the European Association for Machine Translation (EAMT 2024), , pp. 116-132. Sheffield, England.

SignON - a Co-creative Machine Translation for Sign and Spoken Languages (end-of-project results, contributions and lessons learned)

Vandeghinste, V., Shterionov, D., De Sisto, M., Brady, De Coster, M., Leeson, L., Blat, J., Picron, F., Scipioni, M. P., Parikh, A., ten Bosch, L., O’Flaherty, J., Dambre, J., Rijckaert, J., Vanroy, B., Ubieto Nogales, V., Egea Gómez, S., Schuurman, I., Labaka, G., Núñez Marcos, A., Murtagh, I., McGill, E., & Saggion, H.

Proceedings of the 25th Annual Conference of the European Association for Machine Translation (EAMT 2024), , pp. 49-50. Sheffield, England.

SignON Sign Language Translation: Progress and Challenges

Vandeghinste, V., Shterionov, D., De Sisto, M., Brady, De Coster, M., Leeson, L., Blat, J., Picron, F., Scipioni, M. P., Parikh, A., ten Bosch, L., O’Flaherty, J., Dambre, J., Rijckaert, J., Vanroy, B., Ubieto Nogales, V., Egea Gómez, S., Schuurman, I., Labaka, G., Núñez Marcos, A., Murtagh, I., McGill, E., & Saggion, H.

Proceedings of the 24th Annual Conference of the European Association for Machine Translation (EAMT 2023), , pp. 501-502. Tampere, Finland.

BSL-Hansard: A parallel, multimodal corpus of English and interpreted British Sign Language data from parliamentary proceedings

McGill, E. & Saggion, H.

Proceedings of the Second International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL), , pp. 43-48. Tampere, Finland.

Corpus

Part-of-Speech tagging Spanish Sign Language data and its applications in Sign Language machine translation

McGill, E., Chiruzzo, L., Egea Gómez, S., & Saggion, H.

Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023), , pp. 70-76. Tórshavn, Faroe Islands.

Translating Spanish into Spanish Sign Language: Combining Rules and Data-driven Approaches

Chiruzzo, L., McGill, E., Egea Gómez, S., & Saggion, H.

Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022), , pp. 75-83. Gyeongju, Republic of Korea.

Linguistically Enhanced Text to Sign Gloss Machine Translation

Egea Gómez, S., Chiruzzo, L., McGill, E., & Saggion, H.

Proceedings of the 27th International Conference on Natural Language & Information Systems (NLDB 2022), , pp. 172-183. València, Spain.

Syntax-aware Transformers for Neural Machine Translation: The case of text to sign gloss translation

Egea Gómez, McGill, E., & Saggion, H.

Proceedings of the 14th Workshop on Building and Using Comparable Corpora (BUCC 2021), , pp. 18-27. Online.

Misinformation detection

Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models

Przybyła, P., McGill, E. & Saggion, H.

The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), . Suzhou, China.

Know Thine Enemy: Adaptive Attacks on Misinformation Detection Using Reinforcement Learning

Przybyła, P., McGill, E. & Saggion, H.

Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis (WASSA 2024), , pp. 125-140. Bangkok, Thailand.

Sign Language Recognition

Spontaneous Catalan Sign Language Recognition: Data Acquisition and Classification

Garmendia, N., Saggion, H., & McGill, E.

Proceedings of the Third International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL), , pp. 7-15. Geneva, Switzerland.

Accessibility in NLP

Tailoring Automatic Text Simplification Output for Deaf and Hard of Hearing Adults

McGill, E.

Proceedings of the Doctoral Symposium on Natural Language Processing from the PLN.net network 2021, , pp. 50-59. Jaén, Spain.

Phonetics and Sociolinguistics

Investigating articulatory variation in the DoubleTalk corpus: Electromagnetic Articulography evidence of phonetic and speech-style variation

McGill, E.

Master’s thesis, The University of Edinburgh,

An intraspeaker variation study of Scottish /r/ pharyngealisation

Purse, R. & McGill, E.

Lifespans & Styles, 2(2), , pp. 36-44.

The thing about hɪŋ: Production, perception and qualitative data from th:h in Edinburgh speech

McGill, E.

Undergraduate dissertation, The University of Edinburgh,