| tech,8-1-P05-1069,bq | In this paper , we present a novel <term> | training method | </term> for a <term> localized phrase-based | #9557 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,bq | e.g. block bigram features . Our <term> | training algorithm | </term> can easily handle millions of <term> | #9627 Our training algorithm can easily handle millions of features. |
