Mon, Sep 18, 2023 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
PhD Thesis Proposal - Sabyasachee Baruah
Committee Members: Shrikanth Narayanan (Chair), Jonathan May, Kristina Lerman, Emilio Ferrara, and Morteza Dehghani
Title: Character Resolution and Attribution for Narrative Understanding
Abstract: Narrativity is a mechanism through which human beings try to understand the world. We computationally define it as characters interacting with each other during events that relate in time and space. We propose a computational pipeline for narrative understanding and discuss its character centric aspects, resolution and attribution of characters. We contribute computational models and novel datasets towards these tasks in both the textual and visual domain. We work towards scaling our methods to long and multimodal narratives, and analyze how they portray characters across different attribute types and time.
Audiences: Everyone Is Invited
Contact: Melissa Ochoa