ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task - Archive ouverte HAL Access content directly
Conference Papers Year :

ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task

(1) , (2) , (1) , (2) , (2) , (3) , (4) , (3)
1
2
3
4

Abstract

This paper describes the ON-TRAC Consortium translation systems developed for the end-to-end model task of IWSLT Evaluation 2019 for the English→ Portuguese language pair. ON-TRAC Consortium is composed of researchers from three French academic laboratories: LIA (Avignon Univer-sité), LIG (Université Grenoble Alpes), and LIUM (Le Mans Université). A single end-to-end model built as a neural encoder-decoder architecture with attention mechanism was used for two primary submissions corresponding to the two EN-PT evaluations sets: (1) TED (MuST-C) and (2) How2. In this paper, we notably investigate impact of pooling heterogeneous corpora for training, impact of target tokeniza-tion (characters or BPEs), impact of speech input segmenta-tion and we also compare our best end-to-end model (BLEU of 26.91 on MuST-C and 43.82 on How2 validation sets) to a pipeline (ASR+MT) approach.
Fichier principal
Vignette du fichier
IWSLT_2019.pdf (1.03 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02352949 , version 1 (07-11-2019)

Identifiers

  • HAL Id : hal-02352949 , version 1

Cite

Manh Ha Nguyen, Natalia Tomashenko, Marcely Zanon Boito, Antoine Caubrière, Fethi Bougares, et al.. ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task. 16th International Workshop on Spoken Language Translation 2019, Nov 2019, Hong Kong, China. ⟨hal-02352949⟩
179 View
59 Download

Share

Gmail Facebook Twitter LinkedIn More