Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

9

NAACL
2003

favoriteEmaildiscussreport

95views Computational Linguistics» more NAACL 2003»

Cognates Can Improve Statistical Translation Models

13 years 5 months ago

Cognates Can Improve Statistical Translation Models

Download www.isi.edu

We report results of experiments aimed at improving the translation quality by incorporating the cognate information into translation models. The results conﬁrm that the cognate identiﬁcation approach can improve the quality of word alignment in bitexts without the need for extra resources.

Grzegorz Kondrak, Daniel Marcu, Kevin Knight

Real-time Traffic

Cognate Identiﬁcation Approach | Cognate Information | NAACL 2003 | NAACL 2007 | Translation Quality |

claim paper

Related Content

» Determining Recurrent Sound Correspondences by Inducing Translation Models

» A Statistical Model for Lost Language Decipherment

» Issues in pre and posttranslation document expansion untranslatable cognates and missegmen...

» Translation Model Pruning via Usage Statistics for Statistical Machine Translation

» Synchronizing Translated Movie Subtitles

» Enriching Statistical Translation Models Using a DomainIndependent Multilingual Lexical Kn...

» Exploiting Parallel Treebanks to Improve PhraseBased Statistical Machine Translation

» Improving Statistical Machine Translation Efficiency by Triangulation

» A Probability Model to Improve Word Alignment

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2003
Where	NAACL
Authors	Grzegorz Kondrak, Daniel Marcu, Kevin Knight

Comments (0)