Universal Natural Language Processing: How can we build natural language processing systems that work for all of the world’s languages?
While an enormous amount of time, effort, and resources has been invested into developing technology for English, other languages are often overlooked. I am convinced that, in order to make NLP technologies accessible and useful for a wider and more diverse variety of users, more emphasis should be put on developing models for languages besides English, including low-resource languages. Thus, an important goal of my research is to develop computational approaches which perform well across a large variety of languages which might differ from English in their typology as well as the amount of available resources.
Deep Learning · Multilingual NLP · Computational Morphology · NLP for Educational Applications · Language Grounding · NLP for Medical Applications · Low-resource Machine Translation