Katharina von der Wense, Assistant Professor of Computer Science, University of Colorado Boulder
Colloquium held January 11, 2024.
How to build natural language processing systems for languages with limited resources is still an open challenge. In this talk, Katharina Kann discusses how pre-trained multilingual models can be adapted to truly low-resource languages and compare their performance on a novel dataset covering a set of Indigenous American languages, AmericasNLI. Kann ends her presentation by discussing how natural language processing systems for all languages and tasks can potentially be built in the future; specifically, she discussed whether cross-lingual transfer via multilingual models or machine translation might be more promising.
About Katharina von der Wense
Katharina von der Wense is an assistant professor of computer science at the University of Colorado Boulder, and a junior professor at the Johannes Gutenberg University in Mainz, Germany. She leads the VDW Natural Language Processing Group (NALA). She received her PhD from LMU Munich in 2019 and was a postdoc at New York University until she moved to Boulder in 2020. Her work is centered around deep learning for NLP, with a special focus on multilingual NLP and transfer learning, computational morphology, language grounding and NLP for medical and educational applications. Learn more on Katharina's GitHub site.