W. Victor H. Yarlott

School of Computing and Information Sciences


Lecture Information:
  • November 22, 2019
  • 11:30 AM
  • CASE-349

Speaker Bio

W. Victor H. Yarlott is a Ph.D. candidate in the Cognition, Narrative, and Culture (Cognac) Lab at the School of Computing and Information Sciences. He holds a B.Sc. in computer science from the Massachusetts Institute of Technology (MIT) and an M.Eng. from MIT under the direction of Patrick H. Winston. His research focuses on extracting cultural information from narrative text.

Description

There is a wealth of cultural information that can be found in narrative: taboos, rituals, relations, and traditions, to name a few aspects. Cultural information is critical to achieving a full understanding of narrative, with all of the implications it has both within the culture it was written (in-culture) and in cultures that may vary substantially from the original culture (out-culture). Folklorists have identified one form that this cultural information takes: motifs. These motifs are associated with vast stores of cultural knowledge that are not accessible to those outside the cultural group. The goal of my thesis is to detect motifs from three cultural groups in narrative text. To start, I identify cultural groups and salient motifs for those groups. I then propose a pipeline for detecting these salient motifs. Finally, I propose the application of the motif detector to tale type identification, tale type discovery, narrative tracking, or generalized motif detection.