The University of Helsinki Submission to the IWSLT2020 Offline Speech Translation Task

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

This paper describes the University of Helsinki Language Technology group’s participation in the IWSLT 2020 offline speech translation task, addressing the translation of English audio into German text. In line with this year’s task objective, we train both cascade and end-to-end systems for spoken language translation. We opt for an end-to-end multitasking architecture with shared internal representations and a cascade approach that follows a standard procedure consisting of ASR, correction, and MT stages. We also describe the experiments that served as a basis for the submitted systems. Our experiments reveal that multitasking training with shared internal representations is not only possible but allows for knowledge-transfer across modalities.
Originalspråkengelska
Titel på gästpublikationProceedings of the 17th International Conference on Spoken Language Translation (IWSLT)
Antal sidor8
UtgivningsortStroudsburg, PA
FörlagThe Association for Computational Linguistics
Utgivningsdatum9 jul 2020
Sidor95-102
ISBN (elektroniskt)978-1-952148-07-1
DOI
StatusPublicerad - 9 jul 2020
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangInternational Conference on Spoken Language Translation - (held remotely), Seattle, Förenta Staterna (USA)
Varaktighet: 9 jul 202010 jul 2020
Konferensnummer: 17
http://iwslt.org/

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap
  • 6121 Språkvetenskaper

Citera det här