| measure(ment),20-3-P05-1069,ak | We use a <term> maximum likelihood criterion </term> to train a <term> log-linear block bigram model </term> which uses <term> real-valued features </term> ( e.g. a <term> language model score </term> ) as well as <term> binary features </term> based on the <term> block identities </term> themselves , e.g. <term> block bigram features </term> . | #9985 We use a maximum likelihood criterion to train a log-linear block bigram model which uses real-valued features (e.g. alanguage model score) as well as binary features based on the block identities themselves, e.g. block bigram features. | |
| model,12-1-P05-1069,ak | In this paper , we present a novel <term> training method </term> for a <term> localized phrase-based prediction model </term> for <term> statistical machine translation ( SMT ) </term> . | #9941 In this paper, we present a novel training method for alocalized phrase-based prediction model for statistical machine translation (SMT). | |
| model,9-3-P05-1069,ak | We use a <term> maximum likelihood criterion </term> to train a <term> log-linear block bigram model </term> which uses <term> real-valued features </term> ( e.g. a <term> language model score </term> ) as well as <term> binary features </term> based on the <term> block identities </term> themselves , e.g. <term> block bigram features </term> . | #9974 We use a maximum likelihood criterion to train alog-linear block bigram model which uses real-valued features (e.g. a language model score) as well as binary features based on the block identities themselves, e.g. block bigram features. | |
| measure(ment),3-3-P05-1069,ak | We use a <term> maximum likelihood criterion </term> to train a <term> log-linear block bigram model </term> which uses <term> real-valued features </term> ( e.g. a <term> language model score </term> ) as well as <term> binary features </term> based on the <term> block identities </term> themselves , e.g. <term> block bigram features </term> . | #9968 We use amaximum likelihood criterion to train a log-linear block bigram model which uses real-valued features (e.g. a language model score) as well as binary features based on the block identities themselves, e.g. block bigram features. | |
| other,27-3-P05-1069,ak | We use a <term> maximum likelihood criterion </term> to train a <term> log-linear block bigram model </term> which uses <term> real-valued features </term> ( e.g. a <term> language model score </term> ) as well as <term> binary features </term> based on the <term> block identities </term> themselves , e.g. <term> block bigram features </term> . | #9992 We use a maximum likelihood criterion to train a log-linear block bigram model which uses real-valued features (e.g. a language model score) as well asbinary features based on the block identities themselves, e.g. block bigram features. | |
| other,37-3-P05-1069,ak | We use a <term> maximum likelihood criterion </term> to train a <term> log-linear block bigram model </term> which uses <term> real-valued features </term> ( e.g. a <term> language model score </term> ) as well as <term> binary features </term> based on the <term> block identities </term> themselves , e.g. <term> block bigram features </term> . | #10002 We use a maximum likelihood criterion to train a log-linear block bigram model which uses real-valued features (e.g. a language model score) as well as binary features based on the block identities themselves, e.g.block bigram features. | |
| tech,17-1-P05-1069,ak | In this paper , we present a novel <term> training method </term> for a <term> localized phrase-based prediction model </term> for <term> statistical machine translation ( SMT ) </term> . | #9946 In this paper, we present a novel training method for a localized phrase-based prediction model forstatistical machine translation ( SMT ). | |
| tech,8-2-P05-1069,ak | The <term> model </term> predicts <term> blocks with orientation </term> to handle <term> local phrase re-ordering </term> . | #9961 The model predicts blocks with orientation to handlelocal phrase re-ordering. | |
| tech,8-1-P05-1069,ak | In this paper , we present a novel <term> training method </term> for a <term> localized phrase-based prediction model </term> for <term> statistical machine translation ( SMT ) </term> . | #9937 In this paper, we present a noveltraining method for a localized phrase-based prediction model for statistical machine translation (SMT). | |
| other,8-4-P05-1069,ak | Our <term> training algorithm </term> can easily handle millions of <term> features </term> . | #10014 Our training algorithm can easily handle millions offeatures. | |
| tech,1-4-P05-1069,ak | Our <term> training algorithm </term> can easily handle millions of <term> features </term> . | #10007 Ourtraining algorithm can easily handle millions of features. | |
| other,3-2-P05-1069,ak | The <term> model </term> predicts <term> blocks with orientation </term> to handle <term> local phrase re-ordering </term> . | #9956 The model predictsblocks with orientation to handle local phrase re-ordering. | |
| other,14-5-P05-1069,ak | The best system obtains a 18.6 % improvement over the <term> baseline </term> on a standard <term> Arabic-English translation task </term> . | #10030 The best system obtains a 18.6% improvement over the baseline on a standardArabic-English translation task. | |
| model,1-2-P05-1069,ak | The <term> model </term> predicts <term> blocks with orientation </term> to handle <term> local phrase re-ordering </term> . | #9954 Themodel predicts blocks with orientation to handle local phrase re-ordering. | |
| other,32-3-P05-1069,ak | We use a <term> maximum likelihood criterion </term> to train a <term> log-linear block bigram model </term> which uses <term> real-valued features </term> ( e.g. a <term> language model score </term> ) as well as <term> binary features </term> based on the <term> block identities </term> themselves , e.g. <term> block bigram features </term> . | #9997 We use a maximum likelihood criterion to train a log-linear block bigram model which uses real-valued features (e.g. a language model score) as well as binary features based on theblock identities themselves, e.g. block bigram features. | |
| other,10-5-P05-1069,ak | The best system obtains a 18.6 % improvement over the <term> baseline </term> on a standard <term> Arabic-English translation task </term> . | #10026 The best system obtains a 18.6% improvement over thebaseline on a standard Arabic-English translation task. | |
| other,15-3-P05-1069,ak | We use a <term> maximum likelihood criterion </term> to train a <term> log-linear block bigram model </term> which uses <term> real-valued features </term> ( e.g. a <term> language model score </term> ) as well as <term> binary features </term> based on the <term> block identities </term> themselves , e.g. <term> block bigram features </term> . | #9980 We use a maximum likelihood criterion to train a log-linear block bigram model which usesreal-valued features (e.g. a language model score) as well as binary features based on the block identities themselves, e.g. block bigram features. |
