model,11-1-P05-1048,ak subject of much recent debate : do <term> word sense disambigation models </term> help <term> statistical machine translation
measure(ment),16-1-P05-1048,ak sense disambigation models </term> help <term> statistical machine translation quality </term> ? We present empirical results casting
model,3-3-P05-1048,ak assumption . Using a state-of-the-art <term> Chinese word sense disambiguation model </term> to choose <term> translation candidates
other,10-3-P05-1048,ak disambiguation model </term> to choose <term> translation candidates </term> for a typical <term> IBM statistical
tech,15-3-P05-1048,ak translation candidates </term> for a typical <term> IBM statistical MT system </term> , we find that <term> word sense disambiguation
tech,23-3-P05-1048,ak statistical MT system </term> , we find that <term> word sense disambiguation </term> does not yield significantly better
measure(ment),31-3-P05-1048,ak does not yield significantly better <term> translation quality </term> than the <term> statistical machine
tech,35-3-P05-1048,ak translation quality </term> than the <term> statistical machine translation system </term> alone . <term> Error analysis </term>
tech,0-4-P05-1048,ak machine translation system </term> alone . <term> Error analysis </term> suggests several key factors behind
other,16-4-P05-1048,ak including inherent limitations of current <term> statistical MT architectures </term> . Extracting <term> semantic relationships
skrij podrobnosti