Show simple item record

Combining Extraction and Generation for Constructing Belief-Consequence Causal Links

dc.contributor.authorAlexeeva, M.
dc.contributor.authorBeal Cohen, A.A.
dc.contributor.authorSurdeanu, M.
dc.date.accessioned2022-10-24T23:51:22Z
dc.date.available2022-10-24T23:51:22Z
dc.date.issued2022
dc.identifier.citationMaria Alexeeva, Allegra A. Beal Cohen, and Mihai Surdeanu. 2022. Combining Extraction and Generation for Constructing Belief-Consequence Causal Links. In Proceedings of the Third Workshop on Insights from Negative Results in NLP, pages 159–164, Dublin, Ireland. Association for Computational Linguistics.
dc.identifier.isbn9781955917407
dc.identifier.doi10.18653/v1/2022.insights-1.22
dc.identifier.urihttp://hdl.handle.net/10150/666485
dc.description.abstractIn this paper, we introduce and justify a new task—causal link extraction based on beliefs—and do a qualitative analysis of the ability of a large language model—InstructGPT-3—to generate implicit consequences of beliefs. With the language model-generated consequences being promising, but not consistent, we propose directions of future work, including data collection, explicit consequence extraction using rule-based and language modeling-based approaches, and using explicitly stated consequences of beliefs to fine-tune or prompt the language model to produce outputs suitable for the task. © 2022 Association for Computational Linguistics.
dc.language.isoen
dc.publisherAssociation for Computational Linguistics (ACL)
dc.rightsCopyright © 2022 Association for Computational Linguistics. This is an open access article licensed on a Creative Commons Attribution 4.0 International License.
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleCombining Extraction and Generation for Constructing Belief-Consequence Causal Links
dc.typeProceedings
dc.typetext
dc.contributor.departmentDepartment of Linguistics, University of Arizona
dc.contributor.departmentComputer Science Department, University of Arizona
dc.identifier.journalInsights 2022 - 3rd Workshop on Insights from Negative Results in NLP, Proceedings of the Workshop
dc.description.noteOpen access journal
dc.description.collectioninformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.
dc.eprint.versionFinal published version
dc.source.journaltitleInsights 2022 - 3rd Workshop on Insights from Negative Results in NLP, Proceedings of the Workshop
refterms.dateFOA2022-10-24T23:51:22Z


Files in this item

Thumbnail
Name:
2022.insights-1.22.pdf
Size:
88.15Kb
Format:
PDF
Description:
Final Published Version
Download

This item appears in the following Collection(s)

Show simple item record

Copyright © 2022 Association for Computational Linguistics. This is an open access article licensed on a Creative Commons Attribution 4.0 International License.
Except where otherwise noted, this item's license is described as Copyright © 2022 Association for Computational Linguistics. This is an open access article licensed on a Creative Commons Attribution 4.0 International License.