| tech,8-1-P05-1069,ak | In this paper , we present a novel <term> | training method | </term> for a <term> localized phrase-based | #9937 In this paper, we present a novel training method for a localized phrase-based prediction model for statistical machine translation (SMT). | |
| tech,1-4-P05-1069,ak | block bigram features </term> . Our <term> | training algorithm | </term> can easily handle millions of <term> | #10007 Our training algorithm can easily handle millions of features. |
