@inproceedings{d048f06b17064e9ba042fdf16f4c083c,
title = "Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction",
abstract = "An existing domain taxonomy for normalizing content is often assumed when discussing approaches to information extraction, yet often in real-world scenarios there is none. When one does exist, as the information needs shift, it must be continually extended. This is a slow and tedious task, and one that does not scale well. Here we propose an interactive tool that allows a taxonomy to be built or extended rapidly and with a human in the loop to control precision. We apply insights from text summarization and information extraction to reduce the search space dramatically, then leverage modern pretrained language models to perform contextualized clustering of the remaining concepts to yield candidate nodes for the user to review. We show this allows a user to consider as many as 200 taxonomy concept candidates an hour to quickly build or extend a taxonomy to better fit information needs.",
author = "John Hungerford and Chan, {Yee Seng} and Jessica MacBride and Gyori, {Benjamin M.} and Andrew Zupon and Zheng Tang and Egoitz Laparra and Haoling Qiu and Bonan Min and Yan Zverev and Caitlin Hilverman and Max Thomas and Walt Andrews and Keith Alcock and Zeyu Zhang and Michael Reynolds and Mihai Surdeanu and Steve Bethard and Rebecca Sharp",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2nd Workshop on Bridging Human-Computer Interaction and Natural Language Processing, HCI+NLP 2022 ; Conference date: 15-07-2022",
year = "2022",
language = "English (US)",
series = "HCI+NLP 2022 - 2nd Workshop on Bridging Human-Computer Interaction and Natural Language Processing, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "1--10",
editor = "Blodgett, {Su Lin} and Hal Daume and Michael Madaio and Ani Nenkova and Brendan O'Connor and Hanna Wallach and Qian Yang",
booktitle = "HCI+NLP 2022 - 2nd Workshop on Bridging Human-Computer Interaction and Natural Language Processing, Proceedings of the Workshop",
}