Combination of statistical word alignments based on multiple preprocessing schemes

Jakob Elming; Nizar Habash

Combination of statistical word alignments based on multiple preprocessing schemes

Computer Science

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

Abstract

We present an approach to using multiple preprocessing schemes to improve statistical word alignments. We show a relative reduction of alignment error rate of about 38%.

Original language	English (US)
Pages	25-28
Number of pages	4
State	Published - 2007
Event	2007 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007 - Rochester, United States Duration: Apr 22 2007 → Apr 27 2007

Conference

Conference	2007 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007
Country/Territory	United States
City	Rochester
Period	4/22/07 → 4/27/07

ASJC Scopus subject areas

Linguistics and Language
Language and Linguistics
Computer Science Applications

Cite this

Combination of statistical word alignments based on multiple preprocessing schemes. / Elming, Jakob; Habash, Nizar.
2007. 25-28 Paper presented at 2007 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007, Rochester, United States.

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

@conference{ec0d1c36557342eb85789e4f1f780ee7,

title = "Combination of statistical word alignments based on multiple preprocessing schemes",

abstract = "We present an approach to using multiple preprocessing schemes to improve statistical word alignments. We show a relative reduction of alignment error rate of about 38%.",

author = "Jakob Elming and Nizar Habash",

note = "Funding Information: 1The second author was supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-06-C-0023. Any opinions, findings and conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of DARPA. We thank Necip Ayan, Mona Diab, Bonnie Dorr, Abe Ittycheriah, Martin Jansche and Owen Rambow for helpful discussions. Publisher Copyright: {\textcopyright} 2007 Association for Computational Linguistics.; 2007 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007 ; Conference date: 22-04-2007 Through 27-04-2007",

year = "2007",

language = "English (US)",

pages = "25--28",

}

TY - CONF

T1 - Combination of statistical word alignments based on multiple preprocessing schemes

AU - Elming, Jakob

AU - Habash, Nizar

N1 - Funding Information: 1The second author was supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-06-C-0023. Any opinions, findings and conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of DARPA. We thank Necip Ayan, Mona Diab, Bonnie Dorr, Abe Ittycheriah, Martin Jansche and Owen Rambow for helpful discussions. Publisher Copyright: © 2007 Association for Computational Linguistics.

PY - 2007

Y1 - 2007

N2 - We present an approach to using multiple preprocessing schemes to improve statistical word alignments. We show a relative reduction of alignment error rate of about 38%.

AB - We present an approach to using multiple preprocessing schemes to improve statistical word alignments. We show a relative reduction of alignment error rate of about 38%.

UR - http://www.scopus.com/inward/record.url?scp=84878204829&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878204829&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84878204829

SP - 25

EP - 28

T2 - 2007 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007

Y2 - 22 April 2007 through 27 April 2007

ER -

Combination of statistical word alignments based on multiple preprocessing schemes

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this