Show simple item record

dc.contributor.authorKushman, Nate
dc.contributor.authorArtzi, Yoav
dc.contributor.authorZettlemoyer, Luke
dc.contributor.authorBarzilay, Regina
dc.date.accessioned2015-11-09T13:22:15Z
dc.date.available2015-11-09T13:22:15Z
dc.date.issued2014-06
dc.identifier.urihttp://hdl.handle.net/1721.1/99744
dc.description.abstractWe present an approach for automatically learning to solve algebra word problems. Our algorithm reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers in these equations to the problem text. The learning algorithm uses varied supervision, including either full equations or just the final answers. We evaluate performance on a newly gathered corpus of algebra word problems, demonstrating that the system can correctly answer almost 70% of the questions in the dataset. This is, to our knowledge, the first learning result for this task.en_US
dc.description.sponsorshipBattelle Memorial Institute (PO 300662)en_US
dc.description.sponsorshipNational Science Foundation (U.S.) (Grant IIS-0835652)en_US
dc.language.isoen_US
dc.publisherAssociation for Computational Linguisticsen_US
dc.relation.isversionofhttp://acl2014.org/acl2014/P14-1/index.htmlen_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceMIT web domainen_US
dc.titleLearning to Automatically Solve Algebra Word Problemsen_US
dc.typeArticleen_US
dc.identifier.citationKushman, Nate, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay. "Learning to Automatically Solve Algebra Word Problems." 52nd Annual Meeting of the Association for Computational Linguistics (June 2014).en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.mitauthorKushman, Nateen_US
dc.contributor.mitauthorBarzilay, Reginaen_US
dc.relation.journalProceedings of the 52nd Annual Meeting of the Association for Computational Linguisticsen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsKushman, Nate; Artzi, Yoav; Zettlemoyer, Luke; Barzilay, Reginaen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-9254-8422
dc.identifier.orcidhttps://orcid.org/0000-0002-2921-8201
mit.licenseOPEN_ACCESS_POLICYen_US
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record