The Samsung and University of Edinburgh’s submission to IWSLT17

Pawel Przybysz, Marcin Chochowski, Rico Sennrich, Barry Haddow, Alexandra Birch-Mayne

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes the joint submission of Samsung Research and Development, Warsaw, Poland and the University of Edinburgh team to the IWSLT MT task for TED talks. We took part in two translation directions, en-de and de-en. We also participated in the en-de and de-en lectures SLT task. The models have been trained with an attentional encoder-decoder model using the BiDeep model in Nematus. We filtered the training data to reduce the problem of noisy data, and we use back-translated monolingual data for domain-adaptation. We demonstrate the effectiveness of the different techniques that we applied via ablation studies. Our submission system outperforms our baseline, and last year’s University of Edinburgh submission to IWSLT, by more than 5 BLEU.
Original languageEnglish
Title of host publicationProceedings of the 14th International Workshop on Spoken Language Translation
EditorsSakriani Sakti, Masao Utiyama
Place of PublicationTokyo, Japan
Pages23-28
Number of pages6
Publication statusE-pub ahead of print - 15 Dec 2017
Event14th International Workshop on Spoken Language Translation - Tokyo, Japan
Duration: 14 Dec 201715 Dec 2017
http://workshop2017.iwslt.org/

Conference

Conference14th International Workshop on Spoken Language Translation
Abbreviated titleIWSLT 2017
Country/TerritoryJapan
CityTokyo
Period14/12/1715/12/17
Internet address

Fingerprint

Dive into the research topics of 'The Samsung and University of Edinburgh’s submission to IWSLT17'. Together they form a unique fingerprint.

Cite this