Mostra el registre d'ítem simple
The TALP-UPC machine translation systems for WMT19 news translation task: pivoting techniques for low resource MT
dc.contributor.author | Casas Manzanares, Noé |
dc.contributor.author | Rodríguez Fonollosa, José Adrián |
dc.contributor.author | Escolano Peinado, Carlos |
dc.contributor.author | Basta, Christine Raouf Saad |
dc.contributor.author | Ruiz Costa-Jussà, Marta |
dc.contributor.other | Universitat Politècnica de Catalunya. Doctorat en Teoria del Senyal i Comunicacions |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2019-10-09T14:19:29Z |
dc.date.issued | 2019 |
dc.identifier.citation | Casas, N. [et al.]. The TALP-UPC machine translation systems for WMT19 news translation task: pivoting techniques for low resource MT. A: Conference on Machine Translation. "WMT 2019: Fourth Conference on Machine Translation: proceedings of the conference". Stroudsburg, PA: Association for Computational Linguistics, 2019, p. 155-162. |
dc.identifier.isbn | 978-1-950737-27-7 |
dc.identifier.uri | http://hdl.handle.net/2117/169548 |
dc.description.abstract | In this article, we describe the TALP-UPC research group participation in the WMT19 news translation shared task for Kazakh-English. Given the low amount of parallel training data, we resort to using Russian as pivot language, training subword-based statistical translation systems for Russian-Kazakh and Russian-English that were then used to create two synthetic pseudo-parallel corpora for Kazakh-English and English-Kazakh respectively. Finally, a self-attention model based on the decoder part of the Transformer architecture was trained on the two pseudo-parallel corpora. |
dc.format.extent | 8 p. |
dc.language.iso | eng |
dc.publisher | Association for Computational Linguistics |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic |
dc.subject.lcsh | Machine translating |
dc.title | The TALP-UPC machine translation systems for WMT19 news translation task: pivoting techniques for low resource MT |
dc.type | Conference report |
dc.subject.lemac | Traducció automàtica |
dc.contributor.group | Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
dc.identifier.doi | 10.18653/v1/W19-5311 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://www.aclweb.org/anthology/W19-5311 |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 25840852 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO//TEC2015-69266-P/ES/TECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ Y AUDIO/ |
dc.date.lift | 10000-01-01 |
local.citation.author | Casas, N.; Fonollosa, José A. R.; Escolano, C.; Basta, C.; Ruiz, M. |
local.citation.contributor | Conference on Machine Translation |
local.citation.pubplace | Stroudsburg, PA |
local.citation.publicationName | WMT 2019: Fourth Conference on Machine Translation: proceedings of the conference |
local.citation.startingPage | 155 |
local.citation.endingPage | 162 |