XNMT: the eXtensible Neural Machine Translation toolkit

Graham Neubig; Matthias Sperber; Xinyi Wang; Matthieu Felix; Austin Matthews; Sarguna Padmanabhan; Ye Qi; Devendra Sachan; Philip Arthur; Pierre Godard; John Hewitt; Rachid Riad; Liming Wang

XNMT: the eXtensible Neural Machine Translation toolkit

Graham Neubig, Matthias Sperber, Xinyi Wang, Matthieu Felix, Austin Matthews, Sarguna Padmanabhan, Ye Qi, Devendra Sachan, Philip Arthur, Pierre Godard, John Hewitt, Rachid Riad, Liming Wang

Department of Data Science & AI

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

Abstract

This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distinguishes itself from other open-source NMT toolkits by its focus on modular code design, with the purpose of enabling fast iteration in research and replicable, reliable results. In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing. XNMT is available open-source at https://github.com/neulab/xnmt.

Original language	English
Title of host publication	The 13th Conference of The Association for Machine Translation in the Americas - Proceedings
Subtitle of host publication	Vol. 1: MT Researchers’ Track
Editors	Colin Cherry, Graham Neubig
Place of Publication	Boston MA USA
Publisher	Association for Machine Translation in the Americas
Pages	185-192
Number of pages	8
Publication status	Published - Mar 2018
Event	Conference of the Association for Machine Translation in the Americas 2018 - Boston, United States of America Duration: 17 Mar 2018 → 21 Mar 2018 Conference number: 13th http://www.conference.amtaweb.org/

Conference

Conference	Conference of the Association for Machine Translation in the Americas 2018
Abbreviated title	ATMA 2018
Country/Territory	United States of America
City	Boston
Period	17/03/18 → 21/03/18
Internet address	http://www.conference.amtaweb.org/

Access to Document

285174023-oaFinal published version, 90.5 KB

https://www.aclweb.org/anthology/W18-1818/

Cite this

Neubig, G., Sperber, M., Wang, X., Felix, M., Matthews, A., Padmanabhan, S., Qi, Y., Sachan, D., Arthur, P., Godard, P., Hewitt, J., Riad, R., & Wang, L. (2018). XNMT: the eXtensible Neural Machine Translation toolkit. In C. Cherry, & G. Neubig (Eds.), The 13th Conference of The Association for Machine Translation in the Americas - Proceedings : Vol. 1: MT Researchers’ Track (pp. 185-192). Article W18-1818 Association for Machine Translation in the Americas. https://www.aclweb.org/anthology/W18-1818/

@inproceedings{8eec157bd8b44c7cb3d42be00e74fae4,

title = "XNMT: the eXtensible Neural Machine Translation toolkit",

abstract = "This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distinguishes itself from other open-source NMT toolkits by its focus on modular code design, with the purpose of enabling fast iteration in research and replicable, reliable results. In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing. XNMT is available open-source at https://github.com/neulab/xnmt.",

author = "Graham Neubig and Matthias Sperber and Xinyi Wang and Matthieu Felix and Austin Matthews and Sarguna Padmanabhan and Ye Qi and Devendra Sachan and Philip Arthur and Pierre Godard and John Hewitt and Rachid Riad and Liming Wang",

year = "2018",

month = mar,

language = "English",

pages = "185--192",

editor = "Cherry, {Colin } and Neubig, {Graham }",

booktitle = "The 13th Conference of The Association for Machine Translation in the Americas - Proceedings",

publisher = "Association for Machine Translation in the Americas",

note = "Conference of the Association for Machine Translation in the Americas 2018, ATMA 2018 ; Conference date: 17-03-2018 Through 21-03-2018",

url = "http://www.conference.amtaweb.org/",

}

Neubig, G, Sperber, M, Wang, X, Felix, M, Matthews, A, Padmanabhan, S, Qi, Y, Sachan, D, Arthur, P, Godard, P, Hewitt, J, Riad, R & Wang, L 2018, XNMT: the eXtensible Neural Machine Translation toolkit. in C Cherry & G Neubig (eds), The 13th Conference of The Association for Machine Translation in the Americas - Proceedings : Vol. 1: MT Researchers’ Track., W18-1818, Association for Machine Translation in the Americas, Boston MA USA, pp. 185-192, Conference of the Association for Machine Translation in the Americas 2018, Boston, Massachusetts, United States of America, 17/03/18. <https://www.aclweb.org/anthology/W18-1818/>

XNMT: the eXtensible Neural Machine Translation toolkit. / Neubig, Graham; Sperber, Matthias; Wang, Xinyi et al.
The 13th Conference of The Association for Machine Translation in the Americas - Proceedings : Vol. 1: MT Researchers’ Track. ed. / Colin Cherry; Graham Neubig. Boston MA USA: Association for Machine Translation in the Americas, 2018. p. 185-192 W18-1818.

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

TY - GEN

T1 - XNMT

T2 - Conference of the Association for Machine Translation in the Americas 2018

AU - Neubig, Graham

AU - Sperber, Matthias

AU - Wang, Xinyi

AU - Felix, Matthieu

AU - Matthews, Austin

AU - Padmanabhan, Sarguna

AU - Qi, Ye

AU - Sachan, Devendra

AU - Arthur, Philip

AU - Godard, Pierre

AU - Hewitt, John

AU - Riad, Rachid

AU - Wang, Liming

N1 - Conference code: 13th

PY - 2018/3

Y1 - 2018/3

N2 - This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distinguishes itself from other open-source NMT toolkits by its focus on modular code design, with the purpose of enabling fast iteration in research and replicable, reliable results. In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing. XNMT is available open-source at https://github.com/neulab/xnmt.

AB - This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distinguishes itself from other open-source NMT toolkits by its focus on modular code design, with the purpose of enabling fast iteration in research and replicable, reliable results. In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing. XNMT is available open-source at https://github.com/neulab/xnmt.

M3 - Conference Paper

SP - 185

EP - 192

BT - The 13th Conference of The Association for Machine Translation in the Americas - Proceedings

A2 - Cherry, Colin

A2 - Neubig, Graham

PB - Association for Machine Translation in the Americas

CY - Boston MA USA

Y2 - 17 March 2018 through 21 March 2018

ER -

Neubig G, Sperber M, Wang X, Felix M, Matthews A, Padmanabhan S et al. XNMT: the eXtensible Neural Machine Translation toolkit. In Cherry C, Neubig G, editors, The 13th Conference of The Association for Machine Translation in the Americas - Proceedings : Vol. 1: MT Researchers’ Track. Boston MA USA: Association for Machine Translation in the Americas. 2018. p. 185-192. W18-1818