Sitemap

This paper describes the ON-TRAC Consortium translation systems developed for the end-to-end model task of IWSLT Evaluation 2019
for the English-to-Portuguese language pair. ON-TRAC Consortium is composed of researchers from three French academic laboratories: 
LIA (Avignon Université), 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 tokenization (characters or BPEs), impact of speech input segmentation 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.

@misc{nguyen2019ontrac,
  title={ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task},
  author={Ha Nguyen and Natalia Tomashenko and Marcely Zanon Boito and Antoine Caubriere and Fethi Bougares and Mickael Rouvier and Laurent Besacier and Yannick Esteve},
  year={2019},
  eprint={1910.13689},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}

This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, 
offline speech translation and simultaneous speech translation. ON-TRAC Consortium is composed of researchers from three French academic laboratories: 
LIA (Avignon Universit{\'e}), LIG (Universit{\'e} Grenoble Alpes), and LIUM (Le Mans Universit{\'e}). Attention-based encoder-decoder models, 
trained end-to-end, were used for our submissions to the offline speech translation track. Our contributions focused on data augmentation and 
ensembling of multiple models. In the simultaneous speech translation track, we build on Transformer-based wait-k models for the text-to-text subtask. 
For speech-to-text simultaneous translation, we attach a wait-k MT system to a hybrid ASR system. We propose an algorithm to control the latency 
of the ASR+MT cascade and achieve a good latency-quality trade-off on both subtasks. 

@inproceedings{elbayad-etal-2020-trac,
  title = "{ON}-{TRAC} Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at {IWSLT} 2020",
  author = "Elbayad, Maha  and
    Nguyen, Ha  and
    Bougares, Fethi  and
    Tomashenko, Natalia  and
    Caubri{\`e}re, Antoine  and
    Lecouteux, Benjamin  and
    Est{\`e}ve, Yannick  and
    Besacier, Laurent\",
  booktitle = "Proceedings of the 17th International Conference on Spoken Language Translation",
  month = jul,
  year = "2020",
  address = "Online",
  publisher = "Association for Computational Linguistics",
  url = "https://www.aclweb.org/anthology/2020.iwslt-1.2",
  doi = "10.18653/v1/2020.iwslt-1.2",
  pages = "35--43",
  abstract = "This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, offline speech translation and simultaneous speech translation. ON-TRAC Consortium is composed of researchers from three French academic laboratories: LIA (Avignon Universit{\'e}), LIG (Universit{\'e} Grenoble Alpes), and LIUM (Le Mans Universit{\'e}). Attention-based encoder-decoder models, trained end-to-end, were used for our submissions to the offline speech translation track. Our contributions focused on data augmentation and ensembling of multiple models. In the simultaneous speech translation track, we build on Transformer-based wait-k models for the text-to-text subtask. For speech-to-text simultaneous translation, we attach a wait-k MT system to a hybrid ASR system. We propose an algorithm to control the latency of the ASR+MT cascade and achieve a good latency-quality trade-off on both subtasks.",
}