| D08-1090 | also part of the generic language | model training | data . Language model adaptation |
| C04-1103 | Alignment Training For the n-gram TM | model training | , the bilingual name corpus needs |
| C04-1103 | probability distribution . NCM | model training | is carried out in the similar |
| A00-1004 | the lack of parallel corpora for | model training | . Only a few such corpora exist |
| D09-1073 | previously in this section . Reordering | Model Training | : we extract all reordering instances |
| A00-1004 | parallel text mining and translation | model training | . 3.1 The Corpus Using the above |
| A00-1004 | discuss some problems in translation | model training | and show the preliminary CUR |
| C04-1080 | we presented a variation on HMM | model training | in which the tag sequence and |
| C04-1114 | they were not in the language | model training | data . This further improved |
| A00-1004 | parallel text mining , translation | model training | , and some results we obtained |
| A00-1004 | Generated Corpus and Translation | Model Training | In this section , we describe |
| D08-1090 | text . Limiting the translation | model training | in this way simulates the problem |
| D09-1053 | extracted from log files ) for ranking | model training | ( e.g. , Joachims et al. , 2005 |
| D09-1053 | query-document pairs were available for | model training | , the ranker could achieve significantly |
| D08-1090 | training the standard language | model training | . The problem of selecting comparable |
| A00-1004 | adopted , some issues in translation | model training | using the generated parallel |
| D09-1087 | over-fitting , the ability to | model training | data accurately given sufficient |
| D08-1090 | translation system for language | model training | to perform both language and |
| D08-1041 | variant in the original language | model training | data with its corresponding canonical |
| C04-1168 | package ( Och and Ney , 2003 ) . 4.2 | Model Training | In order to quantify translation |
