Projects per year
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.
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
Projects
- 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