Show simple item record

dc.contributor.authorVacareanu, R.
dc.contributor.authorBarbosa, G.C.G.
dc.contributor.authorNoriega-Atala, E.
dc.contributor.authorHahn-Powell, G.
dc.contributor.authorSharp, R.
dc.contributor.authorValenzuela-Escárcega, M.A.
dc.contributor.authorSurdeanu, M.
dc.date.accessioned2022-10-24T23:51:23Z
dc.date.available2022-10-24T23:51:23Z
dc.date.issued2022
dc.identifier.citationRobert Vacareanu, George C.G. Barbosa, Enrique Noriega-Atala, Gus Hahn-Powell, Rebecca Sharp, Marco A. Valenzuela-Escárcega, and Mihai Surdeanu. 2022. A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations, pages 64–70, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
dc.identifier.isbn9781955917742
dc.identifier.doi10.18653/v1/2022.naacl-demo.8
dc.identifier.urihttp://hdl.handle.net/10150/666486
dc.description.abstractWe propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis. Users of our system can specify their requirements through the use of examples, which are collected with a search interface. The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system. Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns. Our code, demo, and documentation is available at https://clulab.github.io/odinsynth/. © 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.titleA Human-machine Interface for Few-shot Rule Synthesis for Information Extraction
dc.typeProceedings
dc.typetext
dc.contributor.departmentUniversity of Arizona
dc.identifier.journalNAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session
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.journaltitleNAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session
refterms.dateFOA2022-10-24T23:51:23Z


Files in this item

Thumbnail
Name:
2022.naacl-demo.8.pdf
Size:
1.055Mb
Format:
PDF
Description:
Final Published Version

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.