OPUS-MT -- Building open translation services for the World

Jörg Tiedemann; Santhosh Thottingal

OPUS-MT -- Building open translation services for the World

Language Technology

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

Abstract

This paper presents OPUS-MT a project that focuses on the development of free resources and tools for machine translation. The current status is a repository of over 1,000 pre-trained neural machine translation models that are ready to be launched in on-line translation services. For this we also provide open source implementations of web applications that can run efficiently on average desktop hardware with a straightforward setup and installation.

Original language	English
Title of host publication	Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
Editors	André Martins [et al.]
Number of pages	2
Place of Publication	Geneva
Publisher	European Association for Machine Translation
Publication date	1 Nov 2020
Pages	479-480
ISBN (Electronic)	978-989-33-0589-8
Publication status	Published - 1 Nov 2020
MoE publication type	A4 Article in conference proceedings
Event	Annual Conference of the European Association for Machine Translation - [Online conference], Lisbon, Portugal Duration: 3 Nov 2020 → 5 Nov 2020 Conference number: 22 https://eamt2020.inesc-id.pt/

Fields of Science

6121 Languages
113 Computer and information sciences

Access to Document

2020.eamt-1_499Final published version, 183 KBLicence: CC BY-ND

Cite this

@inproceedings{d21a5f5e851c4a7295a16ffe694eeff0,

title = "OPUS-MT -- Building open translation services for the World",

abstract = "This paper presents OPUS-MT a project that focuses on the development of free resources and tools for machine translation. The current status is a repository of over 1,000 pre-trained neural machine translation models that are ready to be launched in on-line translation services. For this we also provide open source implementations of web applications that can run efficiently on average desktop hardware with a straightforward setup and installation.",

keywords = "6121 Languages, 113 Computer and information sciences",

author = "J{\"o}rg Tiedemann and Santhosh Thottingal",

year = "2020",

month = nov,

day = "1",

language = "English",

pages = "479--480",

editor = "{Martins [et al.]}, {Andr{\'e} }",

booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",

publisher = "European Association for Machine Translation",

address = "Switzerland",

note = "Annual Conference of the European Association for Machine Translation , EAMT2020 ; Conference date: 03-11-2020 Through 05-11-2020",

url = "https://eamt2020.inesc-id.pt/",

}

Tiedemann, J & Thottingal, S 2020, OPUS-MT -- Building open translation services for the World. in A Martins [et al.] (ed.), Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, Geneva, pp. 479-480, Annual Conference of the European Association for Machine Translation , Lisbon, Portugal, 03/11/2020.

OPUS-MT -- Building open translation services for the World. / Tiedemann, Jörg; Thottingal, Santhosh.
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. ed. / André Martins [et al.]. Geneva: European Association for Machine Translation, 2020. p. 479-480.

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

TY - GEN

T1 - OPUS-MT -- Building open translation services for the World

AU - Tiedemann, Jörg

AU - Thottingal, Santhosh

N1 - Conference code: 22

PY - 2020/11/1

Y1 - 2020/11/1

N2 - This paper presents OPUS-MT a project that focuses on the development of free resources and tools for machine translation. The current status is a repository of over 1,000 pre-trained neural machine translation models that are ready to be launched in on-line translation services. For this we also provide open source implementations of web applications that can run efficiently on average desktop hardware with a straightforward setup and installation.

AB - This paper presents OPUS-MT a project that focuses on the development of free resources and tools for machine translation. The current status is a repository of over 1,000 pre-trained neural machine translation models that are ready to be launched in on-line translation services. For this we also provide open source implementations of web applications that can run efficiently on average desktop hardware with a straightforward setup and installation.

KW - 6121 Languages

KW - 113 Computer and information sciences

UR - https://www.aclweb.org/anthology/2020.eamt-1.61/

M3 - Conference contribution

SP - 479

EP - 480

BT - Proceedings of the 22nd Annual Conference of the European Association for Machine Translation

A2 - Martins [et al.], André

PB - European Association for Machine Translation

CY - Geneva

T2 - Annual Conference of the European Association for Machine Translation

Y2 - 3 November 2020 through 5 November 2020

ER -

OPUS-MT -- Building open translation services for the World

Abstract

Fields of Science

Access to Document

Other files and links

OPUS: The Open Parallel Corpus

FoTran: Found in Translation - Natural Language Understanding with Cross-Lingual Grounding

MeMAD: Methods for Managing Audiovisual Data: Combining Automatic Efficiency with Human Accuracy

OPUS

Cite this

OPUS-MT -- Building open translation services for the World

Abstract

Fields of Science

Access to Document

Other files and links

Projects

OPUS: The Open Parallel Corpus

FoTran: Found in Translation - Natural Language Understanding with Cross-Lingual Grounding

MeMAD: Methods for Managing Audiovisual Data: Combining Automatic Efficiency with Human Accuracy

Datasets

OPUS

Cite this