Loading Events

« All Events

  • This event has passed.

Seminar: Neural networks as cognitive models of syntax

April 8 @ 12:00 pm - 1:00 pm

Speakers of a language generalize their knowledge of syntax in a systematic way to constructions they have never encountered before. This observation has motivated the influential position in linguistics that humans are innately endowed with syntax-specific inductive biases. The applied success of deep learning systems that are not designed with such biases invites a reconsideration of this position. In this talk, Prof. Tal Linzen, Assistant Professor of Linguistics and Data Science at NYU, will review work that uses paradigms from psycholinguistics to examine the syntactic generalization capabilities of contemporary neural network architectures. Alongside some successes, this work suggests that human-like generalization requires stronger inductive biases than those expressed in standard neural network architectures.Hanes 

Details

Date:
April 8
Time:
12:00 pm - 1:00 pm
Event Category:
Event Tags:
Website:
https://unc.zoom.us/j/96765974332?pwd=VGtkY2h3bkVNZGNQMmt6eTFJMzVLdz09

Organizer

UNC Department of Linguistics
Phone:
919-962-1192
Website:
https://linguistics.unc.edu/

Venue

Hanes Hall
University of North Carolina at Chapel Hill
Chapel Hill, NC 27514 United States
+ Google Map
Website:
https://maps.unc.edu/history/unc-museum/hanes-hall/
Would you like to add an event to the calendar or request RENCI Communications coverage for an event?+ Submit Your Event