dc.contributor.author | Ojha, Atul Kr. | |
dc.contributor.author | Malykh, Valentin | |
dc.contributor.author | Karakanta, Alina | |
dc.contributor.author | Liu, Chao-Hong | |
dc.date.accessioned | 2020-12-08T12:09:38Z | |
dc.date.available | 2020-12-08T12:09:38Z | |
dc.date.issued | 2020-12-04 | |
dc.identifier.citation | Ojha, Atul Kr., Malykh, Valentin, Karakanta, Alina, & Liu, Chao-Hong. (2020). Findings of the LoResMT 2020 shared task on zero-shot for low-resource languages. Paper presented at the 3rd Workshop on Technologies for MT of Low Resource Languages, Suzhou, China, 04 December. | en_IE |
dc.identifier.uri | http://hdl.handle.net/10379/16376 | |
dc.description.abstract | This paper presents the findings of the LoResMT 2020 Shared Task on zero-shot translation for low resource languages. This task was organised as part of the 3rd Workshop on Technologies for MT of Low Resource Languages (LoResMT) at AACL-IJCNLP 2020. The focus was on the zero-shot approach as a notable development in Neural Machine Translation to build MT systems for language pairs where parallel corpora are small or even nonexistent. The shared task experience suggests that back-translation and domain adaptation methods result in better accuracy for smallsize datasets. We further noted that, although translation between similar languages is no cakewalk, linguistically distinct languages require more data to give better results. | en_IE |
dc.description.sponsorship | This publication has emanated from research in part supported by the EU H2020 programme under grant agreements 731015 (ELEXIS-European Lexical Infrastructure). We are also grateful to Panlingua Language Processing LLP to provide Hindi, Bhojpuri, Magahi monolingual and parallel corpora. | en_IE |
dc.format | application/pdf | en_IE |
dc.language.iso | en | en_IE |
dc.publisher | Association for Computational Linguistics | en_IE |
dc.relation.ispartof | Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages | en |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Ireland | |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/3.0/ie/ | |
dc.subject | zero-shot translation | en_IE |
dc.subject | low resource languages | en_IE |
dc.subject | LoResMT 2020 | en_IE |
dc.subject | shared task | en_IE |
dc.title | Findings of the LoResMT 2020 shared task on zero-shot for low-resource languages | en_IE |
dc.type | Conference Paper | en_IE |
dc.date.updated | 2020-12-02T02:46:45Z | |
dc.local.publishedsource | https://www.aclweb.org/anthology/2020.loresmt-1.4 | en_IE |
dc.description.peer-reviewed | peer-reviewed | |
dc.contributor.funder | Horizon 2020 | en_IE |
dc.internal.rssid | 23760839 | |
dc.local.contact | Atul Kumar Ojha. Email: atulkumar.ojha@nuigalway.ie | |
dc.local.copyrightchecked | Yes | |
dc.local.version | ACCEPTED | |
dcterms.project | info:eu-repo/grantAgreement/EC/H2020::RIA/731015/EU/European Lexicographic Infrastructure/ELEXIS | en_IE |
nui.item.downloads | 56 | |