other,7-1-P05-1032,ak In this paper we describe a novel <term> data structure </term> for <term> phrase-based statistical
tech,10-1-P05-1032,ak novel <term> data structure </term> for <term> phrase-based statistical machine translation </term> which allows for the <term> retrieval
other,18-1-P05-1032,ak translation </term> which allows for the <term> retrieval </term> of arbitrarily long <term> phrases </term>
other,22-1-P05-1032,ak retrieval </term> of arbitrarily long <term> phrases </term> while simultaneously using less <term>
other,27-1-P05-1032,ak </term> while simultaneously using less <term> memory </term> than is required by current <term>
other,33-1-P05-1032,ak </term> than is required by current <term> decoder implementations </term> . We detail the <term> computational
other,3-2-P05-1032,ak implementations </term> . We detail the <term> computational complexity </term> and <term> average retrieval times </term>
other,6-2-P05-1032,ak computational complexity </term> and <term> average retrieval times </term> for looking up <term> phrase translations
other,12-2-P05-1032,ak retrieval times </term> for looking up <term> phrase translations </term> in our <term> suffix array-based data
other,16-2-P05-1032,ak <term> phrase translations </term> in our <term> suffix array-based data structure </term> . We show how sampling can be used
other,10-3-P05-1032,ak sampling can be used to reduce the <term> retrieval time </term> by <term> orders of magnitude </term>
other,13-3-P05-1032,ak reduce the <term> retrieval time </term> by <term> orders of magnitude </term> with no loss in <term> translation
other,20-3-P05-1032,ak of magnitude </term> with no loss in <term> translation quality </term> . We describe a novel approach to
skrij podrobnosti