Katrin Erk is a professor in the Department of Linguistics at the University of Texas at Austin. Her research expertise is in the area of computational linguistics, especially semantics. Her work is on distributed, flexible approaches to describing word meaning, and on combining them with logic-based representations of sentences and other larger structures. At the word level, she is studying flexible representations of meaning in context, independent of word sense lists. At the sentence level, she is looking into probabilistic frameworks that can draw weighted inferences from combined logical and distributed representations. Katrin Erk completed her dissertation on tree description languages and ellipsis at Saarland University in 2002.
Graded, flexible representations of word meaning that do not need a dictionary
Combining distributional representations for words (and phrases)
logic-based representations at the sentence level
Computational Linguistics, specifically Semantics
Research Labs & Affiliations:
Natural Language Learning reading group
Pengxiang Cheng and Katrin Erk. 2019. Implicit Argument Prediction as Reading Comprehension..
Su Wang, Eric Holgate, Greg Durrett, and Katrin Erk. October 2018. Picking Apart Story Salads. Association for Computational Linguistics. Brussels, Belgium.
Pengxiang Cheng and Katrin Erk. June 2018. Implicit argument prediction with event knowledge. Association for Computational Linguistics. New Orleans, Louisiana.
Su Wang, Greg Durrett, and Katrin Erk. 2018. Modeling semantic plausibility by injecting world knowledge . Association for Computational Linguistics. New Orleans, Louisiana.
Katrin Erk. January 2018. Computational Semantics. .