The MeMAD Submission to the IWSLT 2018 Speech Translation Task

Umut Sulubacak; Jörg Tiedemann; Aku Rouhe; Grönroos Stig-Arne; Mikko Kurimo

The MeMAD Submission to the IWSLT 2018 Speech Translation Task

Umut Sulubacak, Jörg Tiedemann, Aku Rouhe, Grönroos Stig-Arne, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Professional

Abstract

This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time.

All of our systems start by transcribing the audio into text through an automatic speech recognition model trained on the TED-LIUM English Speech Recognition Corpus. Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus and the OpenSubtitles2018 section of the OPUS collection.

In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OpenSubtitles2018 in training significantly improves translation performance. We also experimented with various pre- and postprocessing routines for the NMT module, but we did not have much success with these.

Our best-scoring system attains a BLEU score of 16.45 on the test set for this year’s task.

Original language	English
Title of host publication	Proceedings of the 15th International Workshop on Spoken Language Translation (IWSLT 2018)
Editors	Marco Turchi, Jan Niehues, Marcello Frederico
Number of pages	6
Place of Publication	Bruges
Publication date	30 Oct 2018
Pages	89-94
Publication status	Published - 30 Oct 2018
MoE publication type	D3 Professional conference proceedings
Event	International Workshop on Spoken Language Translation - Brugge, Belgium Duration: 29 Oct 2018 → 30 Oct 2018 Conference number: 15

Fields of Science

113 Computer and information sciences
6121 Languages

Access to Document

Full textFinal published version, 138 KBLicence: Unspecified

Proceedings

1 Active

MeMAD: Methods for Managing Audiovisual Data: Combining Automatic Efficiency with Human Accuracy
Hirvonen, M., Tiedemann, J., Tiittula, L., Sulubacak, U., Vazquez , R. & Koponen, M.
European Commission / Horizon 2020
01/01/2018 → 31/03/2021
Project: Research project

Cite this

@inproceedings{5c66ef060ed64314a30bdbe8f83ddf1c,

title = "The MeMAD Submission to the IWSLT 2018 Speech Translation Task",

abstract = "This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time.All of our systems start by transcribing the audio into text through an automatic speech recognition model trained on the TED-LIUM English Speech Recognition Corpus. Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus and the OpenSubtitles2018 section of the OPUS collection.In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OpenSubtitles2018 in training significantly improves translation performance. We also experimented with various pre- and postprocessing routines for the NMT module, but we did not have much success with these.Our best-scoring system attains a BLEU score of 16.45 on the test set for this year{\textquoteright}s task.",

keywords = "113 Computer and information sciences, 6121 Languages",

author = "Umut Sulubacak and J{\"o}rg Tiedemann and Aku Rouhe and Gr{\"o}nroos Stig-Arne and Mikko Kurimo",

year = "2018",

month = oct,

day = "30",

language = "English",

pages = "89--94",

editor = "Marco Turchi and Jan Niehues and Marcello Frederico",

booktitle = "Proceedings of the 15th International Workshop on Spoken Language Translation (IWSLT 2018)",

note = "International Workshop on Spoken Language Translation, IWSLT ; Conference date: 29-10-2018 Through 30-10-2018",

}

Sulubacak, U , Tiedemann, J, Rouhe, A, Stig-Arne, G & Kurimo, M 2018, The MeMAD Submission to the IWSLT 2018 Speech Translation Task. in M Turchi, J Niehues & M Frederico (eds), Proceedings of the 15th International Workshop on Spoken Language Translation (IWSLT 2018). Bruges, pp. 89-94, International Workshop on Spoken Language Translation, Brugge, Belgium, 29/10/2018.

The MeMAD Submission to the IWSLT 2018 Speech Translation Task. / Sulubacak, Umut ; Tiedemann, Jörg; Rouhe, Aku; Stig-Arne, Grönroos; Kurimo, Mikko.

Proceedings of the 15th International Workshop on Spoken Language Translation (IWSLT 2018). ed. / Marco Turchi; Jan Niehues; Marcello Frederico. Bruges, 2018. p. 89-94.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Professional

TY - GEN

T1 - The MeMAD Submission to the IWSLT 2018 Speech Translation Task

AU - Sulubacak, Umut

AU - Tiedemann, Jörg

AU - Rouhe, Aku

AU - Stig-Arne, Grönroos

AU - Kurimo, Mikko

N1 - Conference code: 15

PY - 2018/10/30

Y1 - 2018/10/30

N2 - This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time.All of our systems start by transcribing the audio into text through an automatic speech recognition model trained on the TED-LIUM English Speech Recognition Corpus. Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus and the OpenSubtitles2018 section of the OPUS collection.In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OpenSubtitles2018 in training significantly improves translation performance. We also experimented with various pre- and postprocessing routines for the NMT module, but we did not have much success with these.Our best-scoring system attains a BLEU score of 16.45 on the test set for this year’s task.

AB - This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time.All of our systems start by transcribing the audio into text through an automatic speech recognition model trained on the TED-LIUM English Speech Recognition Corpus. Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus and the OpenSubtitles2018 section of the OPUS collection.In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OpenSubtitles2018 in training significantly improves translation performance. We also experimented with various pre- and postprocessing routines for the NMT module, but we did not have much success with these.Our best-scoring system attains a BLEU score of 16.45 on the test set for this year’s task.

KW - 113 Computer and information sciences

KW - 6121 Languages

UR - https://workshop2018.iwslt.org/downloads/Proceedings_IWSLT_2018.pdf

M3 - Conference contribution

SP - 89

EP - 94

BT - Proceedings of the 15th International Workshop on Spoken Language Translation (IWSLT 2018)

A2 - Turchi, Marco

A2 - Niehues, Jan

A2 - Frederico, Marcello

CY - Bruges

T2 - International Workshop on Spoken Language Translation

Y2 - 29 October 2018 through 30 October 2018

ER -

The MeMAD Submission to the IWSLT 2018 Speech Translation Task

Abstract

Fields of Science

Access to Document

MeMAD: Methods for Managing Audiovisual Data: Combining Automatic Efficiency with Human Accuracy

Cite this