Show simple item record

dc.contributor.authorShah, Darsh
dc.contributor.authorSchuster, Tal
dc.contributor.authorBarzilay, Regina
dc.date.accessioned2021-10-27T20:22:27Z
dc.date.available2021-10-27T20:22:27Z
dc.date.issued2020
dc.identifier.urihttps://hdl.handle.net/1721.1/135203
dc.description.abstract<jats:p>Online encyclopediae like Wikipedia contain large amounts of text that need frequent corrections and updates. The new information may contradict existing content in encyclopediae. In this paper, we focus on rewriting such dynamically changing articles. This is a challenging constrained generation task, as the output must be consistent with the new information and fit into the rest of the existing document. To this end, we propose a two-step solution: (1) We identify and remove the contradicting components in a target text for a given claim, using a neutralizing stance model; (2) We expand the remaining text to be consistent with the given claim, using a novel two-encoder sequence-to-sequence model with copy attention. Applied to a Wikipedia fact update dataset, our method successfully generates updated sentences for new claims, achieving the highest SARI score. Furthermore, we demonstrate that generating synthetic data through such rewritten sentences can successfully augment the FEVER fact-checking training dataset, leading to a relative error reduction of 13%.1</jats:p>
dc.language.isoen
dc.publisherAssociation for the Advancement of Artificial Intelligence (AAAI)
dc.relation.isversionof10.1609/AAAI.V34I05.6406
dc.rightsCreative Commons Attribution-Noncommercial-Share Alike
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/
dc.sourcearXiv
dc.titleAutomatic Fact-Guided Sentence Modification
dc.typeArticle
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
dc.relation.journalProceedings of the AAAI Conference on Artificial Intelligence
dc.eprint.versionOriginal manuscript
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
eprint.statushttp://purl.org/eprint/status/NonPeerReviewed
dc.date.updated2020-12-01T17:47:32Z
dspace.orderedauthorsShah, D; Schuster, T; Barzilay, R
dspace.date.submission2020-12-01T17:47:35Z
mit.journal.volume34
mit.journal.issue05
mit.licenseOPEN_ACCESS_POLICY
mit.metadata.statusAuthority Work and Publication Information Needed


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record