“Understanding” and prediction in artificial intelligence models
Allyson Ettinger, Assistant Professor, Department of Linguistics, University of Chicago
October 29, 11:30am-1pm, JRL 122
In recent years, the field of natural language processing (NLP) in artificial intelligence has made what appears to be incredible progress, with models even surpassing human performance on certain evaluations. How should we interpret these advances? Have these models achieved so-called language “understanding”? Operating on the premise that “understanding” will necessarily involve the capacity to extract the meaning of language inputs, in this talk I will discuss a series of projects leveraging targeted tests to examine NLP models’ ability to capture linguistic meaning in a systematic fashion. I will discuss implications of the findings both for currently dominant model paradigms in NLP, and for the study of language processing in humans.
More information: https://voices.uchicago.edu/dhforum/10-29-21/