tech,0-1-P05-1067,bq statistical MT architectures </term> . <term> Syntax-based statistical machine translation ( MT ) </term> aims at applying <term> statistical
tech,10-1-P05-1067,bq translation ( MT ) </term> aims at applying <term> statistical models </term> to <term> structured data </term> . In
other,13-1-P05-1067,bq applying <term> statistical models </term> to <term> structured data </term> . In this paper , we present a <term>
tech,7-2-P05-1067,bq </term> . In this paper , we present a <term> syntax-based statistical machine translation system </term> based on a <term> probabilistic synchronous
other,15-2-P05-1067,bq translation system </term> based on a <term> probabilistic synchronous dependency insertion grammar </term> . <term> Synchronous dependency insertion
other,0-3-P05-1067,bq dependency insertion grammar </term> . <term> Synchronous dependency insertion grammars </term> are a version of <term> synchronous
other,8-3-P05-1067,bq insertion grammars </term> are a version of <term> synchronous grammars </term> defined on <term> dependency trees </term>
other,12-3-P05-1067,bq synchronous grammars </term> defined on <term> dependency trees </term> . We first introduce our <term> approach
tech,4-4-P05-1067,bq trees </term> . We first introduce our <term> approach </term> to inducing such a <term> grammar </term>
other,9-4-P05-1067,bq <term> approach </term> to inducing such a <term> grammar </term> from <term> parallel corpora </term>
lr,11-4-P05-1067,bq inducing such a <term> grammar </term> from <term> parallel corpora </term> . Second , we describe the <term> graphical
tech,5-5-P05-1067,bq corpora </term> . Second , we describe the <term> graphical model </term> for the <term> machine translation
other,9-5-P05-1067,bq <term> graphical model </term> for the <term> machine translation task </term> , which can also be viewed as a <term>
tech,20-5-P05-1067,bq </term> , which can also be viewed as a <term> stochastic tree-to-tree transducer </term> . We introduce a <term> polynomial
tech,3-6-P05-1067,bq transducer </term> . We introduce a <term> polynomial time decoding algorithm </term> for the <term> model </term> . We evaluate
tech,9-6-P05-1067,bq time decoding algorithm </term> for the <term> model </term> . We evaluate the <term> outputs </term>
tech,3-7-P05-1067,bq <term> model </term> . We evaluate the <term> outputs </term> of our <term> MT system </term> using
tech,6-7-P05-1067,bq evaluate the <term> outputs </term> of our <term> MT system </term> using the <term> NIST and Bleu automatic
measure(ment),10-7-P05-1067,bq our <term> MT system </term> using the <term> NIST and Bleu automatic MT evaluation software </term> . The result shows that our <term>
tech,5-8-P05-1067,bq </term> . The result shows that our <term> system </term> outperforms the <term> baseline system
skrij podrobnosti