Utilize este identificador para referenciar este registo: http://hdl.handle.net/10071/23672
Registo completo
Campo DCValorIdioma
dc.contributor.authorRei, R.-
dc.contributor.authorBatista, F.-
dc.contributor.authorGuerreiro, N. M.-
dc.contributor.authorCoheur, L.-
dc.contributor.editorBenites, F., Tuggener, D., Hurlimann, M., Cieliebak, M., & Vogel, M.-
dc.date.accessioned2021-12-09T15:07:42Z-
dc.date.available2021-12-09T15:07:42Z-
dc.date.issued2021-
dc.identifier.issn1613-0073-
dc.identifier.urihttp://hdl.handle.net/10071/23672-
dc.description.abstractThis paper describes the model and its corresponding setup, proposed by the Unbabel & INESC-ID team for the 1st Shared Task on Sentence End and Punctuation Prediction in NLG Text (SEPP-NLG 2021). The shared task covers 4 languages (English, German, French and Italian) and includes two subtasks: Subtask 1 - detecting the end of a sentence, and subtask 2 - predicting a range of punctuation marks. Our team proposes a single multilingual and multitask model that is able to produce suitable results for all the languages and subtasks involved. The results show that it is possible to achieve state-of-the-art results using one single multilingual model for both tasks and multiple languages. Using a single multilingual model to solve the task for multiple languages is of particular importance, since training a different model for each language is a cumbersome and time-consuming process.eng
dc.language.isoeng-
dc.publisherCEUR-WS-
dc.relationUIDB/50021/2020-
dc.relation038510-
dc.relation045909-
dc.rightsopenAccess-
dc.titleMultilingual simultaneous sentence end and punctuation predictioneng
dc.typeconferenceObject-
dc.event.title2021 Swiss Text Analytics Conference, SwissText 2021-
dc.event.typeConferênciapt
dc.event.locationWinterthureng
dc.event.date2021-
dc.peerreviewedyes-
dc.journalProceedings of the Swiss Text Analytics Conference 2021-
dc.volume2957-
degois.publication.locationWinterthureng
degois.publication.titleMultilingual simultaneous sentence end and punctuation predictioneng
dc.date.updated2021-12-09T15:01:28Z-
dc.description.versioninfo:eu-repo/semantics/publishedVersion-
dc.subject.fosDomínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informaçãopor
iscte.identifier.cienciahttps://ciencia.iscte-iul.pt/id/ci-pub-82723-
iscte.alternateIdentifiers.scopus2-s2.0-85116401837-
Aparece nas coleções:CTI-CRI - Comunicações a conferências internacionais

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
conferenceobject_82723.pdfVersão Editora622,53 kBAdobe PDFVer/Abrir


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis Logotipo do Orcid 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.