Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Pham, Nghia The
• dc.contributor.author Kruszewski, German
• dc.contributor.author Lazaridou, Angeliki
• dc.contributor.author Baroni, Marco
• dc.date.accessioned 2020-12-15T08:53:23Z
• dc.date.available 2020-12-15T08:53:23Z
• dc.date.issued 2015
• dc.description Comunicació presentada a: 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing celebrat del 26 al 31 de juliol de 2015 a Pequín, Xina.
• dc.description.abstract We introduce C-PHRASE, a distributional semantic model that learns word representations by optimizing context prediction for phrases at all levels in a syntactic tree, from single words to full sentences. C-PHRASE outperforms the state-of-theart C-BOW model on a variety of lexical tasks. Moreover, since C-PHRASE word vectors are induced through a compositional learning objective (modeling the contexts of words combined into phrases), when they are summed, they produce sentence representations that rival those generated by ad-hoc compositional models.en
• dc.description.sponsorship We thank Gemma Boleda and the anonymous reviewers for useful comments. We acknowledge ERC 2011 Starting Independent Research Grant n. 283554 (COMPOSES).
• dc.format.mimetype application/pdf
• dc.identifier.citation The Pham N, Kruszewski G, Lazaridou A, Baroni M. Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model. In: Zong C, Strube M, editors. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers); 2015 Jul 26-31; Beijing, China. Stroudsburg (PA): Association for Computational Linguistics; 2015. p. 971-81. DOI: 10.3115/v1/P15-1094
• dc.identifier.doi http://dx.doi.org/10.3115/v1/P15-1094
• dc.identifier.uri http://hdl.handle.net/10230/46044
• dc.language.iso eng
• dc.publisher ACL (Association for Computational Linguistics)
• dc.relation.ispartof Zong C, Strube M, editors. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers); 2015 Jul 26-31; Beijing, China. Stroudsburg (PA): Association for Computational Linguistics; 2015. p. 971-81
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/283554
• dc.rights © ACL, Creative Commons Attribution 3.0 License (https://creativecommons.org/licenses/by-nc-sa/3.0/)
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by-nc-sa/3.0/
• dc.title Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion