Pattarawat Chormai

Doktorand (stellvertretender Doktorandenvertreter)

Forschungsinteressen: • deep learning and its interpretability • natural language processing • computational methods in sciences • knowledge acquisition and sampling-based decision-marking • data visualisation

Akademischer Werdegang

seit 2019 Doktorand, Max Planck School of Cognition, Leipzig
Promotionsarbeit an der Technischen Universität Berlin (Betreuer: Klaus-Robert Müller & Grégoire Montavon)

2015–2018 Master of Science in Data Science, Technische Universität Eindhoven, Niederlande & Technische Universität Berlin
(Dual-Degree-Program der EIT Digital Master School)

2008–2012 Bachelor of Science in Information Technology, King Mongkut's Institute of Technology, Ladkrabang, Thailand

Lehre

2020/2021 Machine Learning (exercise grading), Technische Universität Berlin

Publikationen

Chormai, P., Ponrawee, P., Jin, C., et al. (2020). Syllable-based neural Thai word segmentation. Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Spain. International Committee on Computational Linguistics, 4619–4637. doi:10.18653/vl/2020.coling-main.407

Chormai, P., Ponrawee, P., & Attapol, R. (2019). AttaCut: A fast and accurate neural Thai word segmenter. Conference on Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada. Retrieved from arXiv:1911.07056.

Rieger, L., Chormai, P., Montavon, G., Hansen, L. K., & Müller, K.-R. (2018). Structuring neural networks for more explainable predictions. In H. J. Escalante et al. (Eds.), Explainable and interpretable models in computer vision and machine learning. The Springer series on challenges in machine learning (pp. 115–131). Springer: Cham, Switzerland.