Show simple item record

NUIG-Panlingua-KMI Hindi-Marathi MT Systems for Similar Language Translation Task @ WMT 2020

dc.contributor.authorOjha, Atul Kr.
dc.contributor.authorRani, Priya
dc.contributor.authorBansal, Akanksha
dc.contributor.authorChakravarthi, Bharathi Raja
dc.contributor.authorKumar, Ritesh
dc.contributor.authorMcCrae, John P.
dc.date.accessioned2020-12-08T15:52:41Z
dc.date.available2020-12-08T15:52:41Z
dc.date.issued2020-11-19
dc.identifier.citationOjha, Atul Kr., Rani, Priya, Bansal, Akanksha, Chakravarthi, Bharathi Raja, Kumar, Ritesh, & McCrae, John P. (2020). NUIG-Panlingua-KMI Hindi-Marathi MT Systems for Similar Language Translation Task @ WMT 2020. Paper presented at the 5th Conference on Machine Translation (WMT20) Online, 19-20 Novemberen_IE
dc.identifier.urihttp://hdl.handle.net/10379/16377
dc.description.abstractNUIG-Panlingua-KMI submission to WMT 2020 seeks to push the state-of-the-art in the Similar language translation task for the Hindi ↔ Marathi language pair. As part of these efforts, we conducted a series of experiments to address the challenges for translation between similar languages. Among the 4 MT systems prepared for this task, 1 PBSMT systems were prepared for Hindi ↔ Marathi each and 1 NMT systems were developed for Hindi ↔ Marathi using Byte Pair Encoding (BPE) of subwords. The results show that different architectures in NMT could be an effective method for developing MT systems for closely related languages. Our Hindi-Marathi NMT system was ranked 8th among the 14 teams that participated and our Marathi-Hindi NMT system was ranked 8th among the 11 teams participated for the task.en_IE
dc.description.sponsorshipThis publication has emanated from research in part supported by the Irish Research Council under grant number SFI/18/CRT/6223 (CRT-Centre for Research Training in Artificial Intelligence) cofunded by the European Regional Development Fund as well as by the EU H2020 programme under grant agreements 731015 (ELEXIS-European Lexical Infrastructure). We are also grateful to the organizers of WMT Similar Translation Shared Task 2020 for providing us the Hindi↔Marathi Parallel Corpus, monolingual and evaluation scores.en_IE
dc.formatapplication/pdfen_IE
dc.language.isoenen_IE
dc.publisherAssociation for Computational Linguisticsen_IE
dc.relation.ispartofProceedings of the Fifth Conference on Machine Translationen
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Ireland
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/3.0/ie/
dc.subjectWMT 2020en_IE
dc.subjectNUIG-Panlingua-KMI Hindi-Marathien_IE
dc.subjectMT Systemsen_IE
dc.subjectSimilar Language Translation Tasken_IE
dc.titleNUIG-Panlingua-KMI Hindi-Marathi MT Systems for Similar Language Translation Task @ WMT 2020en_IE
dc.typeConference Paperen_IE
dc.date.updated2020-12-08T12:36:46Z
dc.local.publishedsourcehttps://www.aclweb.org/anthology/2020.wmt-1.49en_IE
dc.description.peer-reviewedpeer-reviewed
dc.contributor.funderIrish Research Councilen_IE
dc.contributor.funderEuropean Regional Development Funden_IE
dc.contributor.funderHorizon 2020en_IE
dc.internal.rssid23760836
dc.local.contactAtul Kumar Ojha. Email: atulkumar.ojha@nuigalway.ie
dc.local.copyrightcheckedYes
dc.local.versionPUBLISHED
dcterms.projectinfo:eu-repo/grantAgreement/EC/H2020::RIA/731015/EU/European Lexicographic Infrastructure/ELEXISen_IE
nui.item.downloads46


Files in this item

Thumbnail
Name:
license.txt
Size:
5.659Kb
Format:
Text file
View/Open
Thumbnail
Name:
2020.wmt-1.49.pdf
Size:
406.7Kb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Ireland
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs 3.0 Ireland