ADAPTIVE IE: Investigating the Complementarity of Human-AI Collaboration to Adaptively Extract Information on-the-fly

Date

2025-01

Department

Program

Citation of Original Publication

Mondal, Ishani, Michelle Yuan, Anandhavelu N, Aparna Garimella, Francis Ferraro, Andrew Blair-Stanek, Benjamin Van Durme, and Jordan Boyd-Graber. "ADAPTIVE IE: Investigating the Complementarity of Human-AI Collaboration to Adaptively Extract Information on-the-Fly". Edited by Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, and Steven Schockaert. Proceedings of the 31st International Conference on Computational Linguistics. (January 2025): 5870–89. https://aclanthology.org/2025.coling-main.392/

Rights

Attribution 4.0 International

Subjects

Abstract

Information extraction (IE) needs vary over time, where a flexible information extraction (IE) system can be useful. 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 address the problem using our proposed Adaptive IE framework that uses human-in-the-loop refinement to adapt to changing user questions. Through human experiments on three diverse datasets, we demonstrate that Adaptive IE is a domain-agnostic, responsive, efficient framework for helping users access useful information while quickly reorganizing information in response to evolving information needs.