Sheffield submissions for the WMT18 quality estimation shared task

Julia Ive; Carolina Scarton; Frédéric Blain; Lucia Specia

doi:10.18653/v1/W18-6463

Sheffield submissions for the WMT18 quality estimation shared task

Julia Ive, Carolina Scarton, Frédéric Blain, Lucia Specia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

In this paper we present the University of Sheffield submissions for the WMT18 Quality Estimation shared task. We discuss our submissions to all four sub-tasks, where ours is the only team to participate in all language pairs and variations (37 combinations). Our systems show competitive results and outperform the baseline in nearly all cases.

Original language	English
Title of host publication	Proceedings of the Quality Estimation Shared Task at WMT 2018
Subtitle of host publication	Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Publisher	Association for Computational Linguistics
Pages	794-800
Number of pages	7
Volume	2
ISBN (Print)	978-1-948087-81-0
DOIs	https://doi.org/10.18653/v1/W18-6463
Publication status	Published - 2018
Externally published	Yes
Event	Third Conference on Machine Translation - Brussels, Belgium Duration: 31 Oct 2018 → 1 Nov 2018

Conference

Conference	Third Conference on Machine Translation
Abbreviated title	WMT2018
Country/Territory	Belgium
City	Brussels
Period	31/10/18 → 1/11/18

Keywords

Quality estimation shared task

Access to Document

10.18653/v1/W18-6463

http://hdl.handle.net/2436/623556

Cite this

@inproceedings{f12cee38c6814f88b2757ad1f35f013f,

title = "Sheffield submissions for the WMT18 quality estimation shared task",

abstract = "In this paper we present the University of Sheffield submissions for the WMT18 Quality Estimation shared task. We discuss our submissions to all four sub-tasks, where ours is the only team to participate in all language pairs and variations (37 combinations). Our systems show competitive results and outperform the baseline in nearly all cases.",

keywords = "Quality estimation shared task",

author = "Julia Ive and Carolina Scarton and Fr{\'e}d{\'e}ric Blain and Lucia Specia",

year = "2018",

doi = "10.18653/v1/W18-6463",

language = "English",

isbn = "978-1-948087-81-0",

volume = "2",

pages = "794--800",

booktitle = "Proceedings of the Quality Estimation Shared Task at WMT 2018",

publisher = "Association for Computational Linguistics",

note = "Third Conference on Machine Translation, WMT2018 ; Conference date: 31-10-2018 Through 01-11-2018",

}

Ive, J, Scarton, C, Blain, F & Specia, L 2018, Sheffield submissions for the WMT18 quality estimation shared task. in Proceedings of the Quality Estimation Shared Task at WMT 2018: Proceedings of the Third Conference on Machine Translation: Shared Task Papers. vol. 2, Association for Computational Linguistics, pp. 794-800, Third Conference on Machine Translation, Brussels, Belgium, 31/10/18. https://doi.org/10.18653/v1/W18-6463

Sheffield submissions for the WMT18 quality estimation shared task. / Ive, Julia; Scarton, Carolina; Blain, Frédéric et al.
Proceedings of the Quality Estimation Shared Task at WMT 2018: Proceedings of the Third Conference on Machine Translation: Shared Task Papers. Vol. 2 Association for Computational Linguistics, 2018. p. 794-800.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Sheffield submissions for the WMT18 quality estimation shared task

AU - Ive, Julia

AU - Scarton, Carolina

AU - Blain, Frédéric

AU - Specia, Lucia

PY - 2018

Y1 - 2018

N2 - In this paper we present the University of Sheffield submissions for the WMT18 Quality Estimation shared task. We discuss our submissions to all four sub-tasks, where ours is the only team to participate in all language pairs and variations (37 combinations). Our systems show competitive results and outperform the baseline in nearly all cases.

AB - In this paper we present the University of Sheffield submissions for the WMT18 Quality Estimation shared task. We discuss our submissions to all four sub-tasks, where ours is the only team to participate in all language pairs and variations (37 combinations). Our systems show competitive results and outperform the baseline in nearly all cases.

KW - Quality estimation shared task

U2 - 10.18653/v1/W18-6463

DO - 10.18653/v1/W18-6463

M3 - Conference contribution

SN - 978-1-948087-81-0

VL - 2

SP - 794

EP - 800

BT - Proceedings of the Quality Estimation Shared Task at WMT 2018

PB - Association for Computational Linguistics

T2 - Third Conference on Machine Translation

Y2 - 31 October 2018 through 1 November 2018

ER -

Sheffield submissions for the WMT18 quality estimation shared task

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this