Show simple item record

dc.contributor.authorRoy, Subhro
dc.contributor.authorNoseworthy, Michael
dc.contributor.authorPaul, Rohan
dc.contributor.authorPark, Daehyung
dc.contributor.authorRoy, Nicholas
dc.date.accessioned2021-11-03T19:18:05Z
dc.date.available2021-11-03T19:18:05Z
dc.date.issued2019-11
dc.identifier.urihttps://hdl.handle.net/1721.1/137308
dc.description.abstract© 2019 Association for Computational Linguistics. Grounding referring expressions to objects in an environment has traditionally been considered a one-off, ahistorical task. However, in realistic applications of grounding, multiple users will repeatedly refer to the same set of objects. As a result, past referring expressions for objects can provide strong signals for grounding subsequent referring expressions. We therefore reframe the grounding problem from the perspective of coreference detection and propose a neural network that detects when two expressions are referring to the same object. The network combines information from vision and past referring expressions to resolve which object is being referred to. Our experiments show that detecting referring expression coreference is an effective way to ground objects described by subtle visual properties, which standard visual grounding models have difficulty capturing. We also show the ability to detect object coreference allows the grounding model to perform well even when it encounters object categories not seen in the training data.en_US
dc.language.isoen
dc.publisherAssociation for Computational Linguistics (ACL)en_US
dc.relation.isversionofhttp://dx.doi.org/10.18653/V1/K19-1040en_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.sourceAssociation for Computational Linguisticsen_US
dc.titleLeveraging Past References for Robust Language Groundingen_US
dc.typeArticleen_US
dc.identifier.citationRoy, Subhro, Noseworthy, Michael, Paul, Rohan, Park, Daehyung and Roy, Nicholas. 2019. "Leveraging Past References for Robust Language Grounding." CoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference.
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.relation.journalCoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conferenceen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2021-05-03T18:28:16Z
dspace.orderedauthorsRoy, S; Noseworthy, M; Paul, R; Park, D; Roy, Nen_US
dspace.date.submission2021-05-03T18:28:17Z
mit.licensePUBLISHER_POLICY
mit.metadata.statusPublication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record