Toms Bergmanis

Toms Bergmanis

Morphological complexity is not there just to increase data sparsity.—E.M.Bender

About me

I am a PhD student at Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh. My supervisors are Sharon Goldwater and Adam Lopez. My field of study is natural language processing, more specifically semi-supervised and unsupervised machine learning algorithms for morphology induction and reinflection. I also like sub-word unit based (as opposed to word based) natural language processing algorithms.

Publications

Toms Bergmanis and Sharon Goldwater Context Sensitive Neural Lemmatization with Lematus. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2018.
[pdf] [bib] [Lematus code] [Result tables]

Toms Bergmanis, Katharina Kann, Hinrich Schutze, Sharon Goldwater Training Data Augmentation for Low-Resource Morphological Inflection. In Proceedings of the CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection. 2017.
[pdf] [bib]

Toms Bergmanis and Sharon Goldwater From segmentation to analyses: a probabilistic model for unsupervised morphology induction. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. 2017.
[pdf] [bib]

Contact

5.19 Informatics Forum
10 Crichton Street
Edinburgh, EH8 9AB
United Kingdom
T.Bergmanis at sms.ed.ac.uk