I hold an M.Phil. in Speech and Language Processing and a Ph.D. in Computational Linguistics from Trinity College Dublin, where I was affiliated with the Irish Speech and Language Technology Research Centre (School of Linguistic, Speech and Communication Sciences). My doctoral thesis (2019) is entitled “Past, present and future: Computational approaches to mapping Old and Modern Irish cognate verb forms”. Previous to that I studied at Utrecht University, the Netherlands, where I obtained a BA in Linguistics and both a BA and MA in Celtic Languages and Culture. My teaching experience includes undergraduate courses in statistics and computational morphology.
I am currently a Postdoctoral Researcher on the Cardamom project (Comparative Deep Models for Minority and Historical Languages), led by Dr. John McCrae, in the Unit for Linguistic Data, Insight Centre for Data Analytics, National University of Ireland, Galway. While my focus so far has been on finite-state two-level morphology for Old Irish (c. 700–900 A.D), I have a growing interest in the broader area of Natural Language Processing (NLP) for historical texts and languages, and the interface between NLP, lexicography and Digital Humanities. In addition to this, I am dedicated to and involved in the creation of lexical resources and tools for under-resourced historical and minority languages, particularly in the Irish context.
You can contact me at Theodorus.Fransen@insight-centre.org.