CAMPeN- A Novel Human-AI Collaborative Framework for Multi-Perspective Narrative Analytics and Braiding at Scale

Abstract

The project proposes a novel human-AI collaborative framework, called CAMPeN (Collaborative Analytics of Multi-Perspective Narratives), where the AI, given two narratives as input, will first extract sets of candidate clauses w.r.t. Overlap-Unique-Conflict criteria, separately, in a zeroshot fashion. Next, the user will actively verify clauses that were labeled with low confidence by the AI. Finally, the high-confidence-verified clauses will be braided together by the machine to construct the ultimate Overlap-Unique-Conflict style summary, which will be presented to the user.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 06, 2024
Source ID
FA95502310426

Entities

People

  • Shubhra Kanti Karmaker Santu

Organizations

  • Air Force Office of Scientific Research
  • Auburn University
  • United States Air Force

Tags

Readers

  • Computer Vision.
  • Graph Algorithms and Convex Optimization.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.