Natural language processing research has evolved from mainly task-specific models, then to task-independent representation models fine-tuned for various tasks, and finally to fully task-independent language models. This progression addresses a desire for universality, in the sense of handling arbitrary tasks in the same model. Another dimension of universality is the ability to serve arbitrary types of language users, regardless of their choice of language, dialect, or other individual properties. Progress toward universality has historically been addressed largely independently in separate research communities focusing on written, spoken, and signed language, although they share many similarities. This talk will trace the recent progress toward universality in these three language modalities, while highlighting a few pieces of recent work.
Karen Livescu is a Professor at TTI-Chicago, where she has been since 2008. She also has a courtesy faculty appointment at the University of Chicago computer science department and is affiliated with its Data Science Institute. She completed her PhD and postdoc at MIT in the EECS department, after a Bachelor's degree in physics at Princeton University. Her PhD research was on speech recognition and pronunciation modeling with articulatory features. Her research group has since expanded to work on a broad variety of topics in spoken, written, and signed language processing, with a particular interest in representation learning, cross-modality learning, and low-resource settings. She is a Fellow of the IEEE and ISCA. She has served as a program chair/co-chair for Interspeech, ASRU, and ICLR and as an Associate Editor for TACL, IEEE T-PAMI, IEEE T-ASLP, and others.