other,15-1-P05-1034,ak We describe a novel approach to <term> statistical machine translation </term> that combines <term> syntactic information </term> in the <term> source language </term> with recent advances in <term> phrasal translation </term> .
tech,5-2-P05-1034,ak This method requires a <term> source-language </term> <term> dependency parser </term> , <term> target language </term><term> word segmentation </term> and an <term> unsupervised word alignment component </term> .
other,8-2-P05-1034,ak This method requires a <term> source-language </term><term> dependency parser </term> , <term> target language </term> <term> word segmentation </term> and an <term> unsupervised word alignment component </term> .
tech,10-2-P05-1034,ak This method requires a <term> source-language </term><term> dependency parser </term> , <term> target language </term> <term> word segmentation </term> and an <term> unsupervised word alignment component </term> .
other,13-3-P05-1034,ak We align a <term> parallel corpus </term> , project the <term> source dependency parse </term> onto the <term> target sentence </term> , extract <term> dependency treelet translation pairs </term> , and train a <term> tree-based ordering model </term> .
hide detail