The MeMAD Submission to the IWSLT 2018 Speech Translation Task

Show full item record



Permalink

http://hdl.handle.net/10138/263703

Citation

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 .

Title: The MeMAD Submission to the IWSLT 2018 Speech Translation Task
Author: Sulubacak, Umut; Tiedemann, Jörg; Rouhe, Aku; Stig-Arne, Grönroos; Kurimo, Mikko
Other contributor: Turchi, Marco
Niehues, Jan
Frederico, Marcello
Contributor organization: Department of Digital Humanities
Doctoral Programme in Language Studies
Language Technology
Date: 2018-10-30
Language: eng
Number of pages: 6
Belongs to series: Proceedings of the 15th International Workshop on Spoken Language Translation (IWSLT 2018)
URI: http://hdl.handle.net/10138/263703
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.
Subject: 113 Computer and information sciences
6121 Languages
Rights: unspecified
Usage restriction: openAccess
Self-archived version: publishedVersion
Funder: European Commission / Horizon 2020
Grant number:


Files in this item

Total number of downloads: Loading...

Files Size Format View
IWSLT_Speech_Tr ... ask_System_Description.pdf 138.0Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record