Dr Paul Nulty
-
Overview
Overview
Biography
I have always been interested in understanding language, meaning, and cognition in humans and machines. I studied linguistics and computer science at University College Dublin (UCD), and stayed on there to complete my PhD in 2013 under the supervision of Dr. Fintan Costello. My thesis work centred on computational models of conceptual combination, with a final focus on statistical methods for ranking natural language expressions of semantic relations between nouns in English noun-noun combinations.
I then worked on a number of postdoc projects, first on the QUANTESS project at LSE (2013-2015), working on methods for the analysis of social and political texts in R, and then at the Cambridge Concept Lab (2016-2018), where I developed methods for detecting and visualising semantic networks from historical texts. From 2018-2021 I held a Marie-Curie CareerFit fellowship at UCD, working with Corlytics (a Dublin-based RegTech company). I joined Birkbeck as a lecturer in 2021.
Beyond lexical semantics, I am broadly interested in applications of natural language processing to problems in the humanities and social sciences, and I collaborate widely in those areas.
Highlights
I recently published a chapter in the book based on the work of the Cambridge Concept Lab project: Operationalising Conceptual Structure discusses methods for discovering conceptual structures in text and visualising them with semantic networks. (preprint available on BiRON in publications section)
Qualifications
- PhD, University College Dublin, 2014
- BA(Computer Science and Linguistics), University College Dublin, 2005
ORCID
0000-0002-7214-4666 -
Supervision and teaching
Supervision and teaching
Supervision
Current doctoral researchers
-
SHIBU KURIAN
-
TOM SALAAM
-
DIMA BSATA
Teaching
Teaching modules
- Software and Programming II (BUCI088H5)
- Natural Language Processing (COIY064H7)
-
-
Publications
Publications
Article
- Zhang, G. and Nulty, Paul and Lillis, D. (2022) Enhancing legal argument mining with domain pre-training and neural networks. Journal of Data Mining & Digital Humanities NLP4DH, ISSN 2416-5999.
Book Section
- Nulty, Paul (2023) Operationalising conceptual structure. In: de Bolla, P. (ed.) Explorations in the Digital History of Ideas - New Methods and Computational Approaches Search within full text. Cambridge University Press. pp. 54-76. ISBN 9781009263610.
- Zhang, G. and Nulty, Paul and Lillis, D. (2023) Argument mining with graph representation learning. In: Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law. ACM Digital LIbrary. pp. 371-380. ISBN 9798400701979.
- Zhang, G. and Nulty, Paul and Lillis, D. (2022) A decade of legal argumentation mining: datasets and approaches. In: Rosso, P. and Basile, V. and Martínez, R. and Métais, E. and Meziane, F. (eds.) Natural Language Processing and Information Systems - 27th International Conference on Applications of Natural Language to Information Systems, NLDB 2022, Valencia, Spain, June 15–17, 2022, Proceedings. Lecture Notes in Computer Science. Springer. pp. 240-252. ISBN 9783031084720.
- Nulty, Paul (2007) Semantic classification of noun phrases using web counts and learning algorithms. In: Carroll, J.A. and van den Bosch, A. and Zaenen, A. (eds.) Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics: ACL 2007. The Association for Computational Linguistics. pp. 79-84.
- Nulty, Paul and Marquez i Villodre, l. and Wicentowski, R. (2007) UCD-PN: classification of semantic relations between nominals using wordnet and web counts. In: Agirre, E. (ed.) Proceedings of the 4th International Workshop on Semantic Evaluations: SemEval@ACL 2007. The Association for Computer Linguistics. pp. 374-377.