PERSONA-ADAPTIVE IE: Harnessing Human-AI Collaboration to Adaptively Extract Persona-Aware Information

Anonymous

Abstract: The evolving nature of information needs across diverse domains like emergency situations (disease outbreak, earthquake) necessitates a flexible information extraction (IE) system.Despite this, existing IE systems are either fully supervised, requiring expensive human annotations, or fully unsupervised, extracting information that often do not cater to user’s needs. To address these issues, we formally introduce the task of ``IE on-the-fly'', and solve it using our proposed Persona-Adaptive IE framework that leverages human-in-the-loop refinement to adapt to changing user queries. Through human experiments on three diverse datasets, we demonstrate that Persona-Adaptive IE is a domain-generalizable, responsive, efficient framework for helping users access useful information while quickly reorganizing information in response to evolving information needs.

Paper Type: long

Research Area: Information Extraction

Languages Studied: English