CNNs found to jump around more skillfully than RNNs: compositional generalization in seq2seq convolutional networks

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Dessi, Roberto
• dc.contributor.author Baroni, Marco
• dc.date.accessioned 2022-12-02T07:07:27Z
• dc.date.available 2022-12-02T07:07:27Z
• dc.date.issued 2019
• dc.description Comunicació presentada a la 57th Annual Meeting of the Association for Computational Linguistics, celebrada del 28 de juliol al 2 d'agost de 2019 a Florència, Itàlia
• dc.description.abstract Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of “jump around” 0- shot from the component words. Recurrent networks (RNNs) were found to completely fail the most challenging generalization cases. We test here a convolutional network (CNN) on these tasks, reporting hugely improved performance with respect to RNNs. Despite the big improvement, the CNN has however not induced systematic rules, suggesting that the difference between compositional and noncompositional behaviour is not clear-cut.
• dc.format.mimetype application/pdf
• dc.identifier.citation Dessi R, Baroni M. CNNs found to jump around more skillfully than RNNs: compositional generalization in seq2seq convolutional networks. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019; 2019 Jul 28 - Aug 2; Florence, Italy. Stroudsburg: Association for Computational Linguistics; 2019. p. 3919-23.
• dc.identifier.doi https://doi.org/10.18653/v1/P19-1381
• dc.identifier.uri http://hdl.handle.net/10230/55068
• dc.language.iso eng
• dc.publisher ACL (Association for Computational Linguistics)
• dc.relation.ispartof Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019; 2019 Jul 28 - Aug 2; Florence, Italy. Stroudsburg: Association for Computational Linguistics; 2019. p. 3919-23
• dc.rights © ACL, Creative Commons Attribution 4.0 License
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.subject Lingüística computacional
• dc.subject Intel·ligència artificial
• dc.subject Aprenentatge automàtic
• dc.title CNNs found to jump around more skillfully than RNNs: compositional generalization in seq2seq convolutional networks
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion