Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

Marcin Junczys-Dowmunt; Tomasz Dwojak; Hieu Hoang

Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

Marcin Junczys-Dowmunt
, Tomasz Dwojak
, Hieu Hoang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-per-second ratios.

Original language	English
Title of host publication	Proceedings of the International Workshop on Spoken Language Translation 2016
Place of Publication	Japan
Number of pages	8
Volume	1
Edition	1
Publication status	Published - 14 Dec 2016
Event	13th International Workshop on Spoken Language Translation 2016 - Seattle, United States Duration: 8 Dec 2016 → 9 Dec 2016 https://workshop2016.iwslt.org/

Conference

Conference	13th International Workshop on Spoken Language Translation 2016
Abbreviated title	IWSLT 2016
Country/Territory	United States
City	Seattle
Period	8/12/16 → 9/12/16
Internet address	https://workshop2016.iwslt.org/

Keywords / Materials (for Non-textual outputs)

Machine translation
Neural machine translation

Access to Document

IWSLT_2016_paper_4 (1)Accepted author manuscript, 148 KB

https://workshop2016.iwslt.org/downloads/IWSLT_2016_paper_4.pdf

SUMMA - Scalable Understanding of Mulitingual Media
Renals, S. (Principal Investigator), Birch-Mayne, A. (Co-investigator) & Cohen, S. (Co-investigator)
EU government bodies
1/02/16 → 31/01/19
Project: Research

Cite this

@inproceedings{e17df513b3aa4ec5a53f4f4373379b0b,

title = "Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions",

abstract = "In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-per-second ratios.",

keywords = "Machine translation, Neural machine translation",

author = "Marcin Junczys-Dowmunt and Tomasz Dwojak and Hieu Hoang",

year = "2016",

month = dec,

day = "14",

language = "English",

volume = "1",

booktitle = "Proceedings of the International Workshop on Spoken Language Translation 2016",

edition = "1",

note = "13th International Workshop on Spoken Language Translation 2016, IWSLT 2016 ; Conference date: 08-12-2016 Through 09-12-2016",

url = "https://workshop2016.iwslt.org/",

}

Junczys-Dowmunt, M, Dwojak, T & Hoang, H 2016, Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions. in Proceedings of the International Workshop on Spoken Language Translation 2016. 1 edn, vol. 1, 4, Japan, 13th International Workshop on Spoken Language Translation 2016, Seattle, Washington, United States, 8/12/16. <https://workshop2016.iwslt.org/downloads/IWSLT_2016_paper_4.pdf>

TY - GEN

T1 - Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

AU - Junczys-Dowmunt, Marcin

AU - Dwojak, Tomasz

AU - Hoang, Hieu

PY - 2016/12/14

Y1 - 2016/12/14

N2 - In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-per-second ratios.

AB - In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-per-second ratios.

KW - Machine translation

KW - Neural machine translation

M3 - Conference contribution

VL - 1

BT - Proceedings of the International Workshop on Spoken Language Translation 2016

CY - Japan

T2 - 13th International Workshop on Spoken Language Translation 2016

Y2 - 8 December 2016 through 9 December 2016

ER -

Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

Abstract

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Projects

SUMMA - Scalable Understanding of Mulitingual Media

Cite this