Human-in-the-loop Schema Induction

Simple item page
dc.contributor.authorZhang, Tianyi
dc.contributor.authorTham, Isaac
dc.contributor.authorHou, Zhaoyi
dc.contributor.authorRen, Jiaxuan
dc.contributor.authorZhou, Leon
dc.contributor.authorXu, Hainiu
dc.contributor.authorZhang, Li
dc.contributor.authorMartin, Lara J.
dc.contributor.authorDror, Rotem
dc.contributor.authorLi, Sha
dc.contributor.authorJi, Heng
dc.contributor.authorPalmer, Martha
dc.contributor.authorBrown, Susan Windisch
dc.contributor.authorSuchocki, Reece
dc.contributor.authorCallison-Burch, Chris
dc.date.accessioned2024-03-04T15:11:06Z
dc.date.available2024-03-04T15:11:06Z
dc.date.issued2023-07
dc.descriptionProceedings of the 61st Annual Meeting of the Association for Computational Linguistics, July 2023, Toronto, Canada
dc.description.abstractSchema 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. 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.
dc.description.sponsorshipThis 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.
dc.description.urihttps://aclanthology.org/2023.acl-demo.1/
dc.format.extent10 pages
dc.genreconference papers and proceedings
dc.identifierdoi:10.13016/m2ivhe-n9e3
dc.identifier.citationTianyi Zhang, Isaac Tham, Zhaoyi Hou, Jiaxuan Ren, Leon Zhou, Hainiu Xu, Li Zhang, Lara Martin, Rotem Dror, Sha Li, Heng Ji, Martha Palmer, Susan Windisch Brown, Reece Suchocki, and Chris Callison-Burch. 2023. Human-in-the-loop Schema Induction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 1–10, Toronto, Canada. Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.acl-demo.1
dc.identifier.urihttps://doi.org/10.18653/v1/2023.acl-demo.1
dc.identifier.urihttp://hdl.handle.net/11603/31769
dc.language.isoen_US
dc.publisherACL
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.rightsCC BY 4.0 DEED Attribution 4.0 International en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleHuman-in-the-loop Schema Induction
dc.typeText
dcterms.creatorhttps://orcid.org/0000-0002-0623-599X

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
2023.acl-demo.1.pdf
Size:
3.18 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
2023.acl-demo.1.mp4
Size:
92.49 MB
Format:
Video MP4
Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department