Header

UZH-Logo

Maintenance Infos

Samsung and University of Edinburgh’s System for the IWSLT 2019


Wetesko, Joanna; Chochowski, Marcin; Przybysz, Pawel; Williams, Philip; Grundkiewicz, Roman; Sennrich, Rico; Haddow, Barry; Miceli Barone, Antonio Valerio; Birch, Alexandra (2019). Samsung and University of Edinburgh’s System for the IWSLT 2019. In: 16th International Workshop on Spoken Language Translation 2019, Hong Kong, 2 November 2019 - 3 November 2019.

Abstract

This paper describes the joint submission to the IWSLT 2019 English to Czech task by Samsung R&D Institute, Poland, and the University of Edinburgh. Our submission was ultimately produced by combining four Transformer systems through a mixture of ensembling and reranking.

Abstract

This paper describes the joint submission to the IWSLT 2019 English to Czech task by Samsung R&D Institute, Poland, and the University of Edinburgh. Our submission was ultimately produced by combining four Transformer systems through a mixture of ensembling and reranking.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

54 downloads since deposited on 05 Nov 2019
54 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not_refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:3 November 2019
Deposited On:05 Nov 2019 14:35
Last Modified:05 Nov 2019 14:35
Publisher:Zenodo
OA Status:Green
Publisher DOI:https://doi.org/10.5281/zenodo.3525537
Official URL:https://zenodo.org/record/3525537#.XcAIndEo_0p

Download

Green Open Access

Download PDF  'Samsung and University of Edinburgh’s System for the IWSLT 2019'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 114kB
View at publisher
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)