| other,13-2-P05-1057,ak | functions </term> , which depend on the <term> | source language sentence | </term> , the <term> target language sentence | #9621 All knowledge sources are treated as feature functions, which depend on thesource language sentence, the target language sentence and possible additional variables. | |
| model,6-4-P05-1057,ak | information </term> . In this paper , we use <term> | IBM Model 3 alignment properties | </term> , <term> POS correspondence </term> , | #9655 In this paper, we useIBM Model 3 alignment properties, POS correspondence, and bilingual dictionary coverage as features. | |
| model,12-4-P05-1057,ak | Model 3 alignment properties </term> , <term> | POS correspondence | </term> , and <term> bilingual dictionary coverage | #9661 In this paper, we use IBM Model 3 alignment properties,POS correspondence, and bilingual dictionary coverage as features. | |
| tech,8-5-P05-1057,ak | models </term> significantly outperform <term> | IBM translation models | </term> . This paper proposes an <term> alignment | #9679 Our experiments show that log-linear models significantly outperformIBM translation models. | |
| tech,4-5-P05-1057,ak | </term> . Our experiments show that <term> | log-linear models | </term> significantly outperform <term> IBM | #9675 Our experiments show thatlog-linear models significantly outperform IBM translation models. | |
| other,18-2-P05-1057,ak | source language sentence </term> , the <term> | target language sentence | </term> and possible additional <term> variables | #9626 All knowledge sources are treated as feature functions, which depend on the source language sentence, thetarget language sentence and possible additional variables. | |
| other,20-4-P05-1057,ak | bilingual dictionary coverage </term> as <term> | features | </term> . Our experiments show that <term> | #9669 In this paper, we use IBM Model 3 alignment properties, POS correspondence, and bilingual dictionary coverage asfeatures. | |
| tech,9-1-P05-1057,ak | <term> word alignment </term> based on <term> | log-linear models | </term> . All <term> knowledge sources </term> | #9605 We present a framework for word alignment based onlog-linear models. | |
| other,24-2-P05-1057,ak | sentence </term> and possible additional <term> | variables | </term> . <term> Log-linear models </term> allow | #9632 All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible additionalvariables. | |
| other,12-3-P05-1057,ak | be easily extended by incorporating <term> | syntactic information | </term> . In this paper , we use <term> IBM | #9646 Log-linear models allow statistical alignment models to be easily extended by incorporatingsyntactic information. | |
| tech,6-2-P05-1057,ak | knowledge sources </term> are treated as <term> | feature functions | </term> , which depend on the <term> source | #9614 All knowledge sources are treated asfeature functions, which depend on the source language sentence, the target language sentence and possible additional variables. | |
| tech,0-3-P05-1057,ak | additional <term> variables </term> . <term> | Log-linear models | </term> allow <term> statistical alignment | #9634 All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible additional variables.Log-linear models allow statistical alignment models to be easily extended by incorporating syntactic information. | |
| tech,3-3-P05-1057,ak | <term> Log-linear models </term> allow <term> | statistical alignment models | </term> to be easily extended by incorporating | #9637 Log-linear models allowstatistical alignment models to be easily extended by incorporating syntactic information. | |
| other,1-2-P05-1057,ak | <term> log-linear models </term> . All <term> | knowledge sources | </term> are treated as <term> feature functions | #9609 Allknowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible additional variables. | |
| tech,5-1-P05-1057,ak | </term> . We present a framework for <term> | word alignment | </term> based on <term> log-linear models </term> | #9601 We present a framework forword alignment based on log-linear models. | |
| model,16-4-P05-1057,ak | <term> POS correspondence </term> , and <term> | bilingual dictionary coverage | </term> as <term> features </term> . Our experiments | #9665 In this paper, we use IBM Model 3 alignment properties, POS correspondence, andbilingual dictionary coverage as features. |
