Skip to Main content Skip to Navigation
Poster communications

Spoken Language Translation Graphs Re-decoding using Automatic Quality Assessment

Laurent Besacier 1, 2 Benjamin Lecouteux 1, 2, 3 Ngoc Luong 2, 1 Ngoc Le 2, 1
1 LIG [2007-2015] - Laboratoire d'Informatique de Grenoble [2007-2015]
2 GETALP [2007-2015] - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole [2007-2015]
LIG [2007-2015] - Laboratoire d'Informatique de Grenoble [2007-2015]
3 UGA [2016-2019] - Université Grenoble Alpes [2016-2019]
Abstract : This paper investigates how automatic quality assessment of spoken language translation (SLT) can help re-decoding SLT output graphs and improving the overall speech translation performance. Using robust word confidence measures (from both ASR and MT) to re-decode the SLT graph leads to a significant BLEU improvement (more than 2 points) compared to our SLT baseline (French-English task).
Document type :
Poster communications
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download
https://hal.archives-ouvertes.fr/hal-02095256
Contributor : Benjamin Lecouteux <>
Submitted on : Wednesday, April 10, 2019 - 12:11:20 PM
Last modification on : Friday, July 17, 2020 - 11:10:27 AM

File

Vignette du document
poster_ASRU2015.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02095256, version 1

Collections

CNRS | LIG | UGA | LIG_TDCGE_GETALP | POLYTECH-GRENOBLE

Citation

Laurent Besacier, Benjamin Lecouteux, Ngoc Luong, Ngoc Le. Spoken Language Translation Graphs Re-decoding using Automatic Quality Assessment. ASRU, 2015, Scotsdale, United States. ⟨hal-02095256⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

68

Files downloads

131