Home ▻ Colleges & Schools▻College of Science and Engineering▻Staff Profiles

Staff Profiles

Mr Adrian Ó Dubhghaill

BA., MA., M.Sc

Contact Details

Post Doctoral Researcher
E: adrian.odubhghaill@universityofgalway.ie
 
researcher
 

Biography

I am a Post Doctoral researcher at the Insight Centre for Data Analytics where my work focuses on computational techniques and resources to support under-resourced and minority languages. My research interest are in the areas of natural language processing, as well as the Celtic languages, in particular, Old Irish. I created the Würzburg Irish Glosses website (wurzburg.ie) and two Universal Dependencies treebanks of Old Irish glosses.

I received my BA from University College Cork in 2012, after which I went on to receive an MA in Medieval Celtic Languages and Literature (Early Irish and Medieval Welsh) from University College Dublin in 2013. I studied Information Systems for Business Performance in University College Cork, and was awarded an MSc in 2016. I also received a Higher Diploma in Irish (TEG Level C1) from the University of Galway in 2020.

I completed my PhD research in 2024 under the supervision of Dr. John McCrae and Dr. Clodagh Downey. My research addresses the application of natural language processing techniques to diplomatically edited Old Irish text.

Research Interests

Old Irish, Celtic Languages, Minority and Under-resourced Languages, Natural Language Processing, Techniques to Tokenise Languages with Non-Standard Word Spacing.

Conference Publications

  Year Publication
(2024) Proceedings of the 9th Workshop on Linked Data in Linguistics at LREC-COLING 2024
John P. McCrae, Priya Rani, Adrian Doyle, and Bernardo Stearns (2024) Teanga Data Model for Linked Corpora Proceedings of the 9th Workshop on Linked Data in Linguistics at LREC-COLING 2024 [Details]
(2024) Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) at LREC-COLING-2024
Adrian Doyle, John P. McCrae (2024) Developing a Part-of-speech Tagger for Diplomatically Edited Old Irish Text Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) at LREC-COLING-2024 Turin, Italy, [Details]
(2024) Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
Oksana Dereza, Adrian Doyle, Priya Rani, Atul Kr. Ojha, Pádraic Moran, John McCrae (2024) Findings of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Malta, [Details]
(2023) LDK 2023 Conference
Adrian Doyle and Theodorus Fransen and Bernardo Stearns and John Philip McCrae and Oksana Dereza and Priya Rani (2023) The Cardamom Workbench for Historical and Under-Resourced Languages LDK 2023 Conference , pp.109-120 [Details]
(2023) Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
Priya Rani and Koustava Goswami and Adrian Doyle and Theodorus Fransen and Bernardo Stearns and John P. McCrae (2023) Findings of the SIGTYP 2023 Shared task on Cognate and Derivative Detection For Low-Resourced Languages Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP [Details]
(2019) Proceedings of the Celtic Language Technology Workshop 2019
Adrian Doyle and John P. McCrae and Clodagh Downey (2019) A Character-Level LSTM Network Model for Tokenizing the Old Irish text of the Würzburg Glosses on the Pauline Epistles Proceedings of the Celtic Language Technology Workshop 2019 [Details]
(2019) Proceedings of the Celtic Language Technology Workshop 2019
John P. McCrae and Adrian Doyle (2019) Adapting Term Recognition to an Under-Resourced Language: the Case of Irish Proceedings of the Celtic Language Technology Workshop 2019 [Details]
(2018) Proceedings of the 3rd Workshop on Collaboration and Computing for Under-Resourced Languages (CCURL 2018)
Adrian Doyle, John P. McCrae, Clodagh Downey (2018) Preservation of Original Orthography in the Construction of an Old Irish Corpus . In: Claudia Soria, Laurent Besacier, Laurette Pretorius eds. Proceedings of the 3rd Workshop on Collaboration and Computing for Under-Resourced Languages (CCURL 2018) Miyazaki, Japan, , 12-MAY-18 - 12-MAY-18 , pp.67-70 [Details]

Conference Contributions

  Year Publication
(2023) 42nd Annual Harvard Celtic Colloquium,
Adrian Doyle (2023) nitatsoír huili oc tintuúth abélru innalaill nó ocsaigid forsunu nó octabairt ruún essib; Questionable New Translations in the Universal Dependencies Treebank of the St. Gall Glosses, and Why They Don't Matter. [Conference Organising Committee Chairperson], 42nd Annual Harvard Celtic Colloquium, Boston , 05-OCT-23 - 08-OCT-23. [Details]
(2023) The XVIIth International Congress of Celtic Studies,
Adrian Doyle (2023) Orientation and Digital Ogam. Limitations of Unicode's 'Ogham' block and how they can be overcome. [Oral Presentation], The XVIIth International Congress of Celtic Studies, Utrecht, Netherlands , 24-JUL-23 - 28-JUL-23. [Details]
(2023) 36th Irish Conference of Medievalists,
Adrian Doyle (2023) Word Level Standardisation: cenmitha fodailt- indrann insce. [Oral Presentation], 36th Irish Conference of Medievalists, Dublin, Ireland , 22-JUN-23 - 23-JUN-23. [Details]
(2022) Tionól,
Adrian Doyle (2022) ithé se innabriathra; Word-separation and Tokenisation for Diplomatically Edited Old Irish Text. [Oral Presentation], Tionól, Dublin, Ireland , 17-NOV-22 - 19-NOV-22. [Details]
(2022) Cardamom Seminar Series,
Adrian Doyle (2022) The Cardamom Workbench for Historical and Minority Languages. [Invited Oral Presentation], Cardamom Seminar Series, Online , 25-JUL-22 - 25-JUL-22. [Details]
(2022) 35th Irish Conference of Medievalists,
Adrian Doyle (2022) An Analysis of Authorship in the Würzburg Glosses; Computational Approaches. [Oral Presentation], 35th Irish Conference of Medievalists, Belfast , 30-JUN-22 - 02-JUL-22. [Details]

Blog

  Year Publication
(2024) The History of Digital Ogam: How it came to be, and the challenges it faced along the way.
Adrian Doyle (2024) The History of Digital Ogam: How it came to be, and the challenges it faced along the way. The OG(H)AM Project Blog [Details]
(2022) Digital Ogam: Implementation and Implications.
Adrian Doyle (2022) Digital Ogam: Implementation and Implications. The OG(H)AM Project Blog [Details]

Dataset

  Year Publication
(2023) The Diplomatic Würzburg Glosses Treebank.
Adrian Doyle (2023) The Diplomatic Würzburg Glosses Treebank. Universal Dependencies Dataset [Details]
(2023) The Diplomatic St. Gall Glosses Treebank.
Adrian Doyle (2023) The Diplomatic St. Gall Glosses Treebank. Universal Dependencies Dataset [Details]

Online Database

  Year Publication
(2018) Würzburg Irish Glosses.
Adrian Doyle (2018) Würzburg Irish Glosses. Online Database [Details]

Professional Associations

  Association Function From / To
University of Galway PhD Candidate 01-SEP-17 /
Insight SFI Research Centre for Data Analytics PhD Candidate 01-SEP-17 /

Employment

  Employer Position From / To
Insight SFI Research Centre for Data Analytics, University of Galway Research Associate 01-JAN-22 /

Education

  Year Institution Qualification Subject
2016 University College Cork MSc Information Systems for Business Performance
2013 University College Dublin MA Medieval Celtic Languages
2012 University College Cork BA Arts
2020 University of Galway HDip (TEG C1) Gaeilge