this approach is that knowledge concerning translation equivalence of expressions may be directly
other,9-4-I05-2048,bq introduction to <term> statistical machine translation </term> with a focus on practical considerations
other,24-9-H01-1042,bq human translation </term> or a <term> machine translation </term> . Additionally , they were asked
other,10-3-P05-1048,bq disambiguation model </term> to choose <term> translation candidates </term> for a typical <term> IBM
other,26-5-C04-1106,bq </term> , we relied on the idea that <term> translation </term> should preserve <term> meaning </term>
tech,4-1-H05-1095,bq a <term> phrase-based statistical machine translation method </term> , based on <term> non-contiguous
other,30-3-N03-1017,bq <term> heuristic learning </term> of <term> phrase translations </term> from <term> word-based alignments </term>
tech,1-3-H05-1095,bq corpora </term> is proposed . A <term> statistical translation model </term> is also presented that deals
tech,9-1-N04-1022,bq decoding </term> for <term> statistical machine translation </term> . This statistical approach aims
tech,15-2-A94-1007,bq most difficult problems for <term> machine translation ( MT ) systems </term> . The problem is selecting
other,17-3-P05-1034,bq </term> , extract <term> dependency treelet translation pairs </term> , and train a <term> tree-based
model,8-1-H05-1101,bq </term> associated with <term> probabilistic translation models </term> that have recently been adopted
other,28-1-C94-1052,bq <term> lexical entries </term> to their <term> translation equivalents </term> . To help this task we
tech,5-4-H01-1041,bq arguments </term> ) . ( ii ) High quality <term> translation </term> via <term> word sense disambiguation
measure(ment),17-8-P05-1067,bq the <term> IBM models </term> in both <term> translation speed and quality </term> . In this paper
measure(ment),3-1-I05-5003,bq <term> Web </term> . The task of <term> machine translation ( MT ) evaluation </term> is closely related
tech,39-12-J05-1003,bq <term> speech recognition </term> , <term> machine translation </term> , or <term> natural language generation
other,39-3-N03-1017,bq <term> lexical weighting </term> of <term> phrase translations </term> . Surprisingly , learning <term> phrases
other,6-5-H05-1005,bq demonstrate how errors in the <term> machine translations </term> of the input <term> Arabic documents
other,20-1-H05-1101,bq adopted in the literature on <term> machine translation </term> . These <term> models </term> can be
hide detail