Sciweavers

803 search results - page 1 / 161
» Cognates Can Improve Statistical Translation Models
Sort
View
NAACL
2003
13 years 6 months ago
Cognates Can Improve Statistical Translation Models
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...
Grzegorz Kondrak, Daniel Marcu, Kevin Knight
COLING
2002
13 years 4 months ago
Determining Recurrent Sound Correspondences by Inducing Translation Models
I present a novel approach to the determination of recurrent sound correspondences in bilingual wordlists. The idea is to relate correspondences between sounds in wordlists to tra...
Grzegorz Kondrak
ACL
2010
13 years 2 months ago
A Statistical Model for Lost Language Decipherment
In this paper we propose a method for the automatic decipherment of lost languages. Given a non-parallel corpus in a known related language, our model produces both alphabetic map...
Benjamin Snyder, Regina Barzilay, Kevin Knight
12
Voted
IRAL
2003
ACM
13 years 10 months ago
Issues in pre- and post-translation document expansion: untranslatable cognates and missegmented words
Query expansion by pseudo-relevance feedback is a well-established technique in both mono- and cross- lingual information retrieval, enriching and disambiguating the typically ter...
Gina-Anne Levow
NAACL
2007
13 years 6 months ago
Translation Model Pruning via Usage Statistics for Statistical Machine Translation
We describe a new pruning approach to remove phrase pairs from translation models of statistical machine translation systems. The approach applies the original translation system ...
Matthias Eck, Stephan Vogel, Alex Waibel