The LAMBADA dataset: word prediction requiring a broad discourse context

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Boleda, Gemmaca
• dc.contributor.author Paperno, Denisca
• dc.contributor.author Kruszewski, Germanca
• dc.contributor.author Lazaridou, Angelikica
• dc.contributor.author Pham, Quan Ngocca
• dc.contributor.author Bernardi, Raffaellaca
• dc.contributor.author Pezzelle, Sandroca
• dc.contributor.author Baroni, Marcoca
• dc.contributor.author Fernandez, Raquelca
• dc.date.accessioned 2017-08-25T17:17:05Z
• dc.date.available 2017-08-25T17:17:05Z
• dc.date.issued 2016
• dc.description.abstract We introduce LAMBADA, a dataset to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative passages sharing the characteristic that human subjects are able to guess their last word if they are exposed to the whole passage, but not if they only see the last sentence preceding the target word. To succeed on LAMBADA, computational models cannot simply rely on local context, but must be able to keep track of information in the broader discourse. We show that LAMBADA exemplifies a wide range of linguistic phenomena, and that none of several state-ofthe-art language models reaches accuracy above 1% on this novel benchmark. We thus propose LAMBADA as a challenging test set, meant to encourage the development of new models capable of genuine understanding of broad context in natural language text.en
• dc.description.sponsorship This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 655577 (LOVe); ERC 2011 Starting Independent Research Grant n. 283554 (COMPOSES); NWO VIDI grant n. 276-89-008 (Asymmetry in Conversation).en
• dc.format.mimetype application/pdf
• dc.identifier.citation Paperno D, Kruszewski G, Lazaridou A, Pham NQ, Bernardi R, Pezzelle S, Baroni M, Boleda G, Fernandez R. The LAMBADA dataset: word prediction requiring a broad discourse context. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Berlin: Association for Computational Linguistics; 2016. p. 1525-1534.
• dc.identifier.doi http://dx.doi.org/10.18653/v1/P16-1144
• dc.identifier.uri http://hdl.handle.net/10230/32702
• dc.language.iso eng
• dc.publisher ACL (Association for Computational Linguistics)ca
• dc.relation.ispartof Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Berlin: Association for Computational Linguistics; 2016. p. 1525-1534
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/655577
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/283554
• dc.rights © ACL, Creative Commons Attribution 4.0 License
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword LAnguage Modeling Broadened to Account for Discourse Aspects
• dc.subject.keyword Natural Language Processing
• dc.subject.keyword Language modelingen
• dc.subject.keyword Discourseen
• dc.subject.keyword Deep learningen
• dc.title The LAMBADA dataset: word prediction requiring a broad discourse contextca
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion