TY - GEN
T1 - Human-in-The-loop schema induction
AU - Zhang, Tianyi
AU - Tham, Isaac
AU - Hou, Zhaoyi
AU - Ren, Jiaxuan
AU - Zhou, Liyang
AU - Xu, Hainiu
AU - Zhang, Li
AU - Martin, Lara J.
AU - Dror, Rotem
AU - Li, Sha
AU - Ji, Heng
AU - Palmer, Martha
AU - Brown, Susan
AU - Suchocki, Reece
AU - Callison-Burch, Chris
N1 - This research is based upon work supported in part by the DARPA KAIROS Program (contract FA8750-19-2-1004), the DARPA LwLL Program (contract FA8750-19-2-0201), the IARPA BETTER Program (contract 2019-19051600004 and 2019-19051600006), the IARPA HIATUS Program (contract 2022-22072200005), and the NSF (Award 1928631) and National Science Foundation under Grant #2030859 to the Computing Research Association for the CIFellows Project. Approved for Public Release, Distribution Unlimited. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of ODNI, DARPA, IARPA, NSF, or the U.S. Government.
PY - 2023
Y1 - 2023
N2 - Schema induction builds a graph representation explaining how events unfold in a scenario. Existing approaches have been based on information retrieval (IR) and information extraction (IE), often with limited human curation. We demonstrate a human-in-The-loop schema induction system powered by GPT-3.1 We first describe the different modules of our system, including prompting to generate schematic elements, manual edit of those elements, and conversion of those into a schema graph. By qualitatively comparing our system to previous ones, we show that our system not only transfers to new domains more easily than previous approaches but also reduces efforts of human curation thanks to our interactive interface.
AB - Schema induction builds a graph representation explaining how events unfold in a scenario. Existing approaches have been based on information retrieval (IR) and information extraction (IE), often with limited human curation. We demonstrate a human-in-The-loop schema induction system powered by GPT-3.1 We first describe the different modules of our system, including prompting to generate schematic elements, manual edit of those elements, and conversion of those into a schema graph. By qualitatively comparing our system to previous ones, we show that our system not only transfers to new domains more easily than previous approaches but also reduces efforts of human curation thanks to our interactive interface.
UR - http://www.scopus.com/inward/record.url?scp=85162730782&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85162730782&partnerID=8YFLogxK
U2 - 10.18653/v1/2023.acl-demo.1
DO - 10.18653/v1/2023.acl-demo.1
M3 - Conference contribution
AN - SCOPUS:85162730782
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 1
EP - 10
BT - System Demonstrations
PB - Association for Computational Linguistics (ACL)
T2 - 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Y2 - 9 July 2023 through 14 July 2023
ER -