DMCA
Augmenting a Small Parallel Text with Morpho-syntactic Language Resources for Serbian-English Statistical Machine Translation (2005)
Cached
Download Links
| Citations: | 2 - 0 self |
BibTeX
@MISC{Popovic05augmentinga,
author = {Maja Popovic and David Vilar and Hermann Ney and Slobodan Jovičić and Lehrstuhl Für Informatik Vi},
title = {Augmenting a Small Parallel Text with Morpho-syntactic Language Resources for Serbian-English Statistical Machine Translation},
year = {2005}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this work, we examine the quality of several statistical machine translation systems constructed on a small amount of parallel Serbian-English text. The main bilingual parallel corpus consists of about 3k sentences and 20k running words from an unrestricted domain. The translation systems are built on the full corpus as well as on a reduced corpus containing only 200 parallel sentences. A small set of about 350 short phrases from the web is used as additional bilingual knowledge. In addition, we investigate the use of monolingual morpho-syntactic knowledge i.e.
Keyphrases
morpho-syntactic language resource serbian-english statistical machine translation small parallel text full corpus small set main bilingual parallel corpus parallel serbian-english text short phrase additional bilingual knowledge small amount several statistical machine translation system parallel sentence translation system monolingual morpho-syntactic knowledge unrestricted domain
