Skip to main content

University of Michigan School of Information


DS/CSS Seminar: Jacob Eisenstein

02/25/2021, 12:00 pm - 01:00 pm

Computational Models of Language Variation and Change


The study of language variation and change offers unique opportunities for interdisciplinary collaboration. On one hand, computational methods can offer new insights to social science and the digital humanities through the analysis of large-scale corpora of text and metadata. Conversely, social science and the humanities provide theoretical frameworks that are essential for natural language processing algorithms to adequately address the diversity of human language. In this talk, I will describe two collaborations, one in each direction. First, I will present work in the digital humanities, in which a computational model of lexical semantic change leads to a network analysis that offers new perspectives on the movement to abolish slavery in the 19th century United States. Second, I will describe an effort to make natural language processing more robust to dialect variation by building linguistic characterizations of dialect features into automated classifiers through few-shot learning. 


Speaker Bio:


Jacob Eisenstein is a Research Scientist at Google AI. His work spans a range of topics in natural language processing, focusing on computational sociolinguistics, discourse, and machine learning. Prior to joining Google, he was Assistant and Associate Professor of Computer Science at the Georgia Institute of Technology, where he received the NSF CAREER Award and the Air Force Office of Scientific Research Young Investigator Award. Prior to Georgia Tech, Jacob was a Postdoctoral researcher at Carnegie Mellon, where he initiated a line of research using latent variable machine learning methods to analyze social media data for insights in sociolinguistics and other areas of social science. He completed his Ph.D. at MIT in 2008, winning the George M. Sprowls dissertation award for his research on computational models of speech and gesture. Jacob's research has been featured in the New York Times, National Public Radio, and the BBC. Thanks to his brief appearance in If These Knishes Could Talk, Jacob has a Bacon number of 2.


The University of Michigan Data Science / Computational Social Science faculty host a seminar series that features invited talks, research presentations and informal work-in-progress discussions. A list of the scheduled speakers for Winter 2021 (January-April) is available here

Link to talk.