Show simple item record

dc.contributor.authorAn, Aixiu
dc.contributor.authorQian, Peng
dc.contributor.authorWilcox, Ethan
dc.contributor.authorLevy, Roger
dc.date.accessioned2021-11-03T17:21:57Z
dc.date.available2021-11-03T17:21:57Z
dc.date.issued2019
dc.identifier.urihttps://hdl.handle.net/1721.1/137251
dc.description.abstract© 2019 Association for Computational Linguistics Neural language models have achieved state-of-the-art performances on many NLP tasks, and recently have been shown to learn a number of hierarchically-sensitive syntactic dependencies between individual words. However, equally important for language processing is the ability to combine words into phrasal constituents, and use constituent-level features to drive downstream expectations. Here we investigate neural models' ability to represent constituent-level features, using coordinated noun phrases as a case study. We assess whether different neural language models trained on English and French represent phrase-level number and gender features, and use those features to drive downstream expectations. Our results suggest that models use a linear combination of NP constituent number to drive CoordNP/verb number agreement. This behavior is highly regular and even sensitive to local syntactic context, however it differs crucially from observed human behavior. Models have less success with gender agreement. Models trained on large corpora perform best, and there is no obvious advantage for models trained using explicit syntactic supervision.en_US
dc.language.isoen
dc.publisherAssociation for Computational Linguisticsen_US
dc.relation.isversionof10.18653/v1/d19-1287en_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.titleRepresentation of Constituents in Neural Language Models: Coordination Phrase as a Case Studyen_US
dc.typeArticleen_US
dc.identifier.citationAn, Aixiu, Qian, Peng, Wilcox, Ethan and Levy, Roger. 2019. "Representation of Constituents in Neural Language Models: Coordination Phrase as a Case Study." EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference.
dc.contributor.departmentMassachusetts Institute of Technology. Department of Brain and Cognitive Sciences
dc.relation.journalEMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, 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.updated2021-04-12T18:52:39Z
dspace.orderedauthorsAn, A; Qian, P; Wilcox, E; Levy, Ren_US
dspace.date.submission2021-04-12T18:52:39Z
mit.licensePUBLISHER_POLICY
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record