Aleksei Nazarov & Gaja Jarosz. 2021. The Credit Problem in Parametric Stress: A Statistical Approach. Glossa 6(1). 1-26. https://doi.org/10.16995/glossa.5884 In this paper, we introduce a novel domain-general, statistical learning model for P&P grammars: the Expectation Driven Parameter Learner (EDPL). We show that the EDPL provides a mathematically principled solution to the Credit Problem (Dresher 1999).… Continue reading →
Jarosz, Gaja. January 2019. Hidden Structure and Ambiguity in Phonological Learning . Second Annual Meeting of the Society for Computation in LinguisticsNew York, New York.
Nazarov, Aleksei & Jarosz, Gaja. 2017. Learning Parametric Stress without Domain-Specific Mechanisms. Proceedings of the 2016 Annual Meetings on Phonology, USC. http://dx.doi.org/10.3765/amp.v4i0.4010
Nazarov, Aleksei and Gaja Jarosz. Oct 2016. Learning parametric stress without domain-specific mechanisms. Annual Meetings on Phonology 2016, University of Southern California.
Jarosz, Gaja. Oct 2016. Refining UG: Connecting Phonological Theory and Learning. Invited talk, NELS 47. University of Massachusetts Amherst, MA.
Jarosz, Gaja. 2015. Expectation Driven Learning of Phonology. University of Massachusetts manuscript.
Jarosz, Gaja. 2016. Investigating the Efficiency of Parsing Strategies for the Gradual Learning Algorithm. In Dimensions of Stress. Cambridge University Press.
Jarosz, Gaja. 2013. Naive Parameter Learning for Optimality Theory – the Hidden Structure Problem. In Proceedings of the 40th Annual Meeting of the North East Linguistic Society.
Jarosz, Gaja. 2013. Learning with Hidden Structure in Optimality Theory and Harmonic Grammar: Beyond Robust Interpretive Parsing. In Phonology 30(1), 27-71. Cambridge University Press.
Jarosz, Gaja. 2006. Richness of the Base and Probabilistic Unsupervised Learning in Optimality Theory. Association for Computational Linguistics: Proceedings of the Eighth Meeting of the ACL Special Interest Group in Computational Phonology.
