LIUM's Contributions to the WMT2019 News Translation Task: Data and Systems for German⇆French Language Pairs

被引：0

作者：

Bougares, Fethi ^{[1
]}

Wottawa, Jane ^{[1
]}

Baillot, Anne ^{[2
]}

Barrault, Loic ^{[1
]}

机构：

[1] Le Mans Univ, LIUM, Le Mans, France

[2] Le Mans Univ, 3LAM, Le Mans, France

来源：

FOURTH CONFERENCE ON MACHINE TRANSLATION (WMT 2019) | 2019年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes the neural machine translation (NMT) systems of the LIUM Laboratory developed for the French <-> German news translation task of the Fourth Conference on Machine Translation (WMT 2019). The chosen language pair is included for the first time in the WMT news translation task. We describe how the training and the evaluation data was created. We also present our participation in the French <-> German translation directions using self-attentional Transformer networks with small and big architectures.

引用

页码：129 / 133

页数：5

共 9 条

[1] Bougares Fethi, 2019, P 2019 DIG HUM C UTR
[2] Koehn Philipp., 2007, P 45 ANN M ASS COMPU, P177, DOI 10.3115/1557769.1557821
[3] Moore Robert C., 2010, ACL, P220
[4] Ott M., 2018, P 3 C MACH TRANSL RE, P1
[5] Ott M, 2019, NAACL HLT 2019: THE 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES: PROCEEDINGS OF THE DEMONSTRATIONS SESSION, P48
[6] BLEU: a method for automatic evaluation of machine translation
Papineni, K
Roukos, S
Ward, T
Zhu, WJ
[J]. 40TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 2002, : 311 - 318
[7] Rousseau Anthony, 2013, Prague Bulletin of Mathematical Linguistics, P73, DOI 10.2478/pralin-2013-0013
[8] Sennrich R, 2016, PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, P86
[9] Vaswani A., 2017, PROC NEURIPS, P1

← 1 →