OpenNMT: Open-Source Toolkit for Neural Machine Translation

被引：696

作者：

Klein, Guillaume ^{[1
]}

Kim, Yoon ^{[2
]}

Deng, Yuntian ^{[2
]}

Senellart, Jean ^{[1
]}

Rush, Alexander M. ^{[2
]}

机构：

[1] SYSTRAN, Paris, France

[2] Harvard SEAS, Cambridge, MA USA

来源：

PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017): SYSTEM DEMONSTRATIONS | 2017年

关键词：

D O I：

10.18653/v1/P17-4012

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We describe an open-source toolkit for neural machine translation (NMT). The toolkit prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research into model architectures, feature representations, and source modalities, while maintaining competitive performance and reasonable training requirements. The toolkit consists of modeling and translation support, as well as detailed pedagogical documentation about the underlying techniques.

引用

页码：67 / 72

页数：6

共 25 条

[1]

[Anonymous], 2014, CORR

[2]

Bahdanau D, 2016, Arxiv, DOI [arXiv:1409.0473, DOI 10.48550/ARXIV.1409.0473]

[3]

Bowman S. R., 2016, P 20 SIGNLL C COMP N, P10, DOI [DOI 10.18653/V1/K16-1002, 10.18653/v1/K16-1002]

[4]

Chan W., 2015, Listen, attend and spell

[5]

Cho K, 2014, ARXIV14061078, P1724, DOI [DOI 10.3115/V1/D14-1179, 10.3115/V1/D14-1179]

[6]

Chopra S., 2016, P 2016 C N AM CHAPT, P93, DOI DOI 10.18653/V1/N16-1012

[7]

Chung Junyoung, 2014, Empirical evaluation of gated recurrent neural networks on sequence modeling

[8]

Crego Josep, 2016, ARXIV160206023

[9]

Dean J., 2012, ADV NEURAL INFORM PR, V25, P1223, DOI DOI 10.5555/2999134.2999271

[10]

Deng Y., 2016, CoRR

← 1 2 3 →