Conference proceeding
Human-in-the-Loop Schema Induction
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-DEMO 2023, VOL 3, pp 1-10
01 Jan 2023
Abstract
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 (IF). often with limited human curation. We demonstrate a human-in-the-loop schema induction system powered by GET-3,l- 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 oration thanks to our interactive interface,
Metrics
1 Record Views
Details
- Title
- Human-in-the-Loop Schema Induction
- Creators
- Tianyi Zhang - University of PennsylvaniaIsaac Than - University of PennsylvaniaZhaoyi Hou - University of PennsylvaniaJiaxuan Ren - University of PennsylvaniaLiyang Zhou - University of PennsylvaniaHainiu Xu - University of PennsylvaniaLi Zhang - University of PennsylvaniaLara J. Martin - University of PennsylvaniaRotem Dror - University of PennsylvaniaSha Li - University of Illinois ChicagoHang Ji - University of Illinois ChicagoMartha Palmer - University of Colorado BoulderSusan Brown - University of Colorado BoulderReece Suchocki - University of Colorado BoulderChris Callison-Burch - University of Pennsylvania
- Contributors
- D Bollegala (Editor)R Huang (Editor)A Ritter (Editor)
- Publication Details
- PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-DEMO 2023, VOL 3, pp 1-10
- Publisher
- Association for Computational Linguistics
- Number of pages
- 10
- Grant note
- 2030859 / National Science Foundation; National Science Foundation (NSF) FA8750-19-2-0201 / DARPA LwLL Program 2019-19051600004; 2019-19051600006 / IARPA BETTER Program 1928631 / NSF; National Science Foundation (NSF) FA8750-19-2-1004 / DARPA KAIROS Program; United States Department of Defense 2022-22072200005 / IARPA HIATUS Program
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Web of Science ID
- WOS:001181040500001
- Other Identifier
- 991022123341004721