I specialize in computational models of grammar learning and grammatical variation.
My research is centered around three ideas:
First, that meaning and usage are essential parts of language
Second, that computational models can encode and test linguistic theories
Third, that linguistics should be applied to practical problems
I currently am working on global-scale computational dialectology as the combination of grammar induction and geospatial text classification. The goal is to model regional syntactic variation so accurately that the model can be used to predict an individual’s region-of-origin.
- Dunn J. (2019) Frequency vs. Association for Constraint Selection in Usage-Based Construction Grammar. In Proceedings of the NAACL 2019 Workshop on Cognitive Modeling and Computational Linguistics.: 117-128.
- Dunn J. (2019) Global Syntactic Variation in Seven Languages: Towards a Computational Dialectology. Frontiers in Artificial Intelligence: Language and Computation.
- Dunn J. (2019) Modeling Global Syntactic Variation in English Using Dialect Classification. In Proceedings of the NAACL 2019 Sixth Workshop on NLP for Similar Languages, Varieties and Dialects: 42-53.
- Dunn J. and Adams B. (2019) Mapping Languages and Demographics with Georeferenced Corpora. In Poceedings of Geocomputation 2019.
- Dunn J. (2018) Finding variants for construction-based dialectometry: A corpus-based approach to regional CxGs. Cognitive Linguistics 29(2): 275-311. http://dx.doi.org/10.1515/cog-2017-0029.