Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

58.848 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Departaments
  • Departament de Ciències de la Computació
  • Articles de revista
  • View Item
  •   DSpace Home
  • E-prints
  • Departaments
  • Departament de Ciències de la Computació
  • Articles de revista
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Semantic and syntactic information for neural machine translation: Injecting features to the transformer

Thumbnail
View/Open
Armengol-Estapé-Costa-jussà2021_Article_SemanticAndSyntacticInformatio.pdf (729,2Kb)
Share:
 
 
10.1007/s10590-021-09264-2
 
  View Usage Statistics
Cita com:
hdl:2117/347441

Show full item record
Armengol Estapé, Jordi
Ruiz Costa-Jussà, MartaMés informacióMés informació
Document typeArticle
Defense date2021-05-18
Rights accessOpen Access
Attribution 4.0 International
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution 4.0 International
ProjectLUNAR - Lifelong UNiversal lAnguage Representation (EC-H2020-947657)
Abstract
Introducing factors such as linguistic features has long been proposed in machine translation to improve the quality of translations. More recently, factored machine translation has proven to still be useful in the case of sequence-to-sequence systems. In this work, we investigate whether this gains hold in the case of the state-of-the-art architecture in neural machine translation, the Transformer, instead of recurrent architectures. We propose a new model, the Factored Transformer, to introduce an arbitrary number of word features in the source sequence in an attentional system. Specifically, we suggest two variants depending on the level at which the features are injected. Moreover, we suggest two combination mechanisms for the word features and words themselves. We experiment both with classical linguistic features and semantic features extracted from a linked data database, and with two low-resource datasets. With the best-found configuration, we show improvements of 0.8 BLEU over the baseline Transformer in the IWSLT German-to-English task. Moreover, we experiment with the more challenging FLoRes English-to-Nepali benchmark, which includes both low-resource and very distant languages, and obtain an improvement of 1.2 BLEU. These improvements are achieved with linguistic and not with semantic information.
CitationArmengol, J.; Costa-jussà, M.R. Semantic and syntactic information for neural machine translation: Injecting features to the transformer. "Machine translation", 18 Maig 2021, vol. 35, p. 3-17. 
URIhttp://hdl.handle.net/2117/347441
DOI10.1007/s10590-021-09264-2
ISSN0922-6567
Publisher versionhttps://link.springer.com/article/10.1007/s10590-021-09264-2
Collections
  • Departament de Ciències de la Computació - Articles de revista [943]
  • VEU - Grup de Tractament de la Parla - Articles de revista [172]
  • Life Sciences - Articles de revista [308]
Share:
 
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
Armengol-Estapé ... AndSyntacticInformatio.pdf729,2KbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • About This Repository
  • Contact Us
  • Send Feedback
  • Inici de la pàgina