Joshua: An Open Source Toolkit for Parsing-based Machine Translation

Zhifei Li; Chris Callison-Burch; Chris Dyer; Juri Ganitkevitch; Sanjeev Khudanpur; Lane Schwartz; Wren N.G. Thornton; Jonathan Weese; Omar F. Zaidan

Joshua: An Open Source Toolkit for Parsing-based Machine Translation

Zhifei Li, Chris Callison-Burch, Chris Dyer, Juri Ganitkevitch, Sanjeev Khudanpur, Lane Schwartz, Wren N.G. Thornton, Jonathan Weese, Omar F. Zaidan

Linguistics

Research output: Contribution to conference › Paper › peer-review

Abstract

We describe Joshua, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for synchronous context free grammars (SCFGs): chart-parsing, ngram language model integration, beamand cube-pruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We demonstrate that the toolkit achieves state of the art translation performance on the WMT09 French-English translation task.

Original language	English (US)
Pages	135-139
Number of pages	5
State	Published - 2009
Event	4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009 - Athens, Greece Duration: Mar 30 2009 → Mar 31 2009

Conference

Conference	4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009
Country/Territory	Greece
City	Athens
Period	3/30/09 → 3/31/09

ASJC Scopus subject areas

Software
Language and Linguistics
Human-Computer Interaction

Library availability

Discover UIUC Full Text

Cite this

Li, Z., Callison-Burch, C., Dyer, C., Ganitkevitch, J., Khudanpur, S., Schwartz, L., Thornton, W. N. G., Weese, J., & Zaidan, O. F. (2009). Joshua: An Open Source Toolkit for Parsing-based Machine Translation. 135-139. Paper presented at 4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009, Athens, Greece.

Joshua: An Open Source Toolkit for Parsing-based Machine Translation. / Li, Zhifei; Callison-Burch, Chris; Dyer, Chris et al.
2009. 135-139 Paper presented at 4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009, Athens, Greece.

Research output: Contribution to conference › Paper › peer-review

Li, Z, Callison-Burch, C, Dyer, C, Ganitkevitch, J, Khudanpur, S, Schwartz, L, Thornton, WNG, Weese, J & Zaidan, OF 2009, 'Joshua: An Open Source Toolkit for Parsing-based Machine Translation', Paper presented at 4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009, Athens, Greece, 3/30/09 - 3/31/09 pp. 135-139.

Li Z, Callison-Burch C, Dyer C, Ganitkevitch J, Khudanpur S, Schwartz L et al.. Joshua: An Open Source Toolkit for Parsing-based Machine Translation. 2009. Paper presented at 4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009, Athens, Greece.

@conference{69b30551a4ca4019952323db05dc9f84,

title = "Joshua: An Open Source Toolkit for Parsing-based Machine Translation",

abstract = "We describe Joshua, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for synchronous context free grammars (SCFGs): chart-parsing, ngram language model integration, beamand cube-pruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We demonstrate that the toolkit achieves state of the art translation performance on the WMT09 French-English translation task.",

author = "Zhifei Li and Chris Callison-Burch and Chris Dyer and Juri Ganitkevitch and Sanjeev Khudanpur and Lane Schwartz and Thornton, {Wren N.G.} and Jonathan Weese and Zaidan, {Omar F.}",

note = "This research was supported in part by the Defense Advanced Research Projects Agency{\textquoteright}s GALE program under Contract No. HR0011-06-2-0001 and the National Science Foundation under grants No. 0713448 and 0840112. The views and findings are the authors{\textquoteright} alone.; 4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009 ; Conference date: 30-03-2009 Through 31-03-2009",

year = "2009",

language = "English (US)",

pages = "135--139",

}

TY - CONF

T1 - Joshua

T2 - 4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009

AU - Li, Zhifei

AU - Callison-Burch, Chris

AU - Dyer, Chris

AU - Ganitkevitch, Juri

AU - Khudanpur, Sanjeev

AU - Schwartz, Lane

AU - Thornton, Wren N.G.

AU - Weese, Jonathan

AU - Zaidan, Omar F.

N1 - This research was supported in part by the Defense Advanced Research Projects Agency’s GALE program under Contract No. HR0011-06-2-0001 and the National Science Foundation under grants No. 0713448 and 0840112. The views and findings are the authors’ alone.

PY - 2009

Y1 - 2009

N2 - We describe Joshua, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for synchronous context free grammars (SCFGs): chart-parsing, ngram language model integration, beamand cube-pruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We demonstrate that the toolkit achieves state of the art translation performance on the WMT09 French-English translation task.

AB - We describe Joshua, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for synchronous context free grammars (SCFGs): chart-parsing, ngram language model integration, beamand cube-pruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We demonstrate that the toolkit achieves state of the art translation performance on the WMT09 French-English translation task.

UR - http://www.scopus.com/inward/record.url?scp=84873459298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873459298&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84873459298

SP - 135

EP - 139

Y2 - 30 March 2009 through 31 March 2009

ER -

Joshua: An Open Source Toolkit for Parsing-based Machine Translation

Abstract

Conference

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this