What you can cram into a single $&!#* vector: probing sentence embeddings for linguistic properties

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Conneau, Alexis
• dc.contributor.author Kruszewski, German
• dc.contributor.author Lample, Guillaume
• dc.contributor.author Barrault, Loïc
• dc.contributor.author Baroni, Marco
• dc.date.accessioned 2020-12-10T09:39:20Z
• dc.date.available 2020-12-10T09:39:20Z
• dc.date.issued 2018
• dc.description Comunicació presentada a: 56th Annual Meeting of the Association for Computational Linguistics celebrat del 15 al 20 de juliol de 2018 a Melbourne, Australia.
• dc.description.abstract Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. “Downstream” tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods.en
• dc.format.mimetype application/pdf
• dc.identifier.citation Conneau A, Kruszewski G, Lample G, Berrault L, Baroni M. What you can cram into a single $&!#* vector: probing sentence embeddings for linguistic properties. In: Gurevych I, Miyao Y, editors. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2018 Jul 15-20; Melbourne, Autralia. Stroudsburg (PA): Association for Computational Linguistics; 2016. p. 2126-36. DOI: 10.18653/v1/P18-1198
• dc.identifier.doi http://dx.doi.org/10.18653/v1/P18-1198
• dc.identifier.uri http://hdl.handle.net/10230/45965
• dc.language.iso eng
• dc.publisher ACL (Association for Computational Linguistics)
• dc.relation.ispartof Gurevych I, Miyao Y, editors. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2018 Jul 15-20; Melbourne, Autralia. Stroudsburg (PA): Association for Computational Linguistics; 2016. p. 2126-36
• dc.rights © ACL, Creative Commons Attribution 4.0 License (https://creativecommons.org/licenses/by/4.0/)
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.title What you can cram into a single $&!#* vector: probing sentence embeddings for linguistic propertiesen
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion