dc.contributor.author | Artetxe Zurutuza, Mikel | |
dc.contributor.author | Labaka Intxauspe, Gorka | |
dc.contributor.author | Agirre Bengoa, Eneko | |
dc.date.accessioned | 2024-10-17T12:53:02Z | |
dc.date.available | 2024-10-17T12:53:02Z | |
dc.date.issued | 2018 | |
dc.identifier.citation | Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics 1: 789-798 (2018) | es_ES |
dc.identifier.uri | http://hdl.handle.net/10810/69991 | |
dc.description.abstract | Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution. Our method succeeds in all tested scenarios and obtains the best published results in standard datasets, even surpassing previous supervised systems. Our implementation is released as an open source project at https://github.com/artetxem/vecmap. | es_ES |
dc.description.sponsorship | This research was partially supported by the Spanish MINECO (TUNER TIN2015-65308-C5-1-R, MUSTER PCIN-2015-226 and TADEEP TIN2015-70214-P, cofunded by EU FEDER), the UPV/EHU (excellence research group), and the NVIDIA GPU grant program. Mikel Artetxe enjoys a doctoral grant from the Spanish MECD. | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | ACL | es_ES |
dc.rights | info:eu-repo/semantics/openAccess | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es/ | * |
dc.title | A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings | es_ES |
dc.type | info:eu-repo/semantics/conferenceObject | es_ES |
dc.rights.holder | (c) 2018 The authors under the Creative Commons Attribution 4.0 International (CC BY 4.0) | es_ES |
dc.relation.publisherversion | https://doi.org/10.18653/v1/P18-1073 | es_ES |
dc.identifier.doi | 10.18653/v1/P18-1073 | |
dc.departamentoes | Lenguajes y sistemas informáticos | es_ES |
dc.departamentoeu | Hizkuntza eta sistema informatikoak | es_ES |