tech,10-1-H01-1041,bq been developing a <term> Korean-to-English machine translation system </term><term> CCLINC (
tech,30-1-H01-1042,bq </term> , to the <term> output </term> of <term> machine translation ( MT ) systems </term> . We believe
tech,24-2-H01-1042,bq </term> and the <term> development </term> of <term> machine translation systems </term> . This , the
other,16-6-H01-1042,bq from duplicating the experiment using <term> machine translation output </term> . Subjects were
other,11-8-H01-1042,bq human translations </term> , others were <term> machine translation outputs </term> . The subjects
other,24-9-H01-1042,bq expert human translation </term> or a <term> machine translation </term> . Additionally , they
tech,28-4-H01-1055,bq </term> can be overcome by employing <term> machine learning techniques </term> . In this paper
tech,5-1-P01-1070,bq </term> . We describe a set of <term> supervised machine learning </term> experiments centering on
tech,8-1-N03-1004,bq of <term> ensemble methods </term> in <term> machine learning </term> and other areas of <term>
tech,11-1-N03-2036,bq unigram model </term> for <term> statistical machine translation </term> that uses a much simpler
tech,6-2-P03-1050,bq model </term> is based on <term> statistical machine translation </term> and it uses an <term> English
tech,4-1-C04-1035,bq difference . This paper presents a <term> machine learning </term> approach to bare <term> sluice
tech,26-3-C04-1035,bq dataset </term> , and run two different <term> machine learning algorithms </term> : <term> SLIPPER
tech,0-1-C04-1103,bq <term> referring expressions </term> . <term> Machine transliteration/back-transliteration </term>
tech,8-2-C04-1103,bq this paper , a novel framework for <term> machine transliteration/back transliteration </term>
tech,9-1-N04-1022,bq MBR ) decoding </term> for <term> statistical machine translation </term> . This statistical approach
tech,1-4-N04-1024,bq structure </term> . A <term> support vector machine </term> uses these <term> features </term> to
other,16-1-H05-1005,bq multilingual input </term> to correct errors in <term> machine translation </term> and thus improve the
tech,6-4-H05-1005,bq </term> . Further , the use of multiple <term> machine translation systems </term> provides yet
other,6-5-H05-1005,bq . We demonstrate how errors in the <term> machine translations </term> of the input <term> Arabic
hide detail