| tech,4-1-H05-1012,bq | phrases </term> . This paper presents a <term> | maximum entropy word alignment algorithm | </term> for <term> Arabic-English </term> based | #7253 This paper presents amaximum entropy word alignment algorithm for Arabic-English based on supervised training data. |
| other,10-1-H05-1012,bq | word alignment algorithm </term> for <term> | Arabic-English | </term> based on <term> supervised training | #7259 This paper presents a maximum entropy word alignment algorithm forArabic-English based on supervised training data. |
| lr,13-1-H05-1012,bq | <term> Arabic-English </term> based on <term> | supervised training data | </term> . We demonstrate that it is feasible | #7262 This paper presents a maximum entropy word alignment algorithm for Arabic-English based onsupervised training data. |
| lr,8-2-H05-1012,bq | demonstrate that it is feasible to create <term> | training material | </term> for problems in <term> machine translation | #7274 We demonstrate that it is feasible to createtraining material for problems in machine translation and that a mixture of supervised and unsupervised methods yields superior performance. |
| tech,13-2-H05-1012,bq | training material </term> for problems in <term> | machine translation | </term> and that a mixture of <term> supervised | #7279 We demonstrate that it is feasible to create training material for problems inmachine translation and that a mixture of supervised and unsupervised methods yields superior performance. |
| tech,20-2-H05-1012,bq | translation </term> and that a mixture of <term> | supervised and unsupervised methods | </term> yields superior <term> performance </term> | #7286 We demonstrate that it is feasible to create training material for problems in machine translation and that a mixture ofsupervised and unsupervised methods yields superior performance. |
| measure(ment),26-2-H05-1012,bq | unsupervised methods </term> yields superior <term> | performance | </term> . The <term> probabilistic model </term> | #7292 We demonstrate that it is feasible to create training material for problems in machine translation and that a mixture of supervised and unsupervised methods yields superiorperformance. |
| model,1-3-H05-1012,bq | superior <term> performance </term> . The <term> | probabilistic model | </term> used in the <term> alignment </term> | #7295 Theprobabilistic model used in the alignment directly models the link decisions. |
| tech,6-3-H05-1012,bq | probabilistic model </term> used in the <term> | alignment | </term> directly models the <term> link decisions | #7300 The probabilistic model used in thealignment directly models the link decisions. |
| other,10-3-H05-1012,bq | alignment </term> directly models the <term> | link decisions | </term> . Significant improvement over traditional | #7304 The probabilistic model used in the alignment directly models thelink decisions. |
| tech,4-4-H05-1012,bq | Significant improvement over traditional <term> | word alignment techniques | </term> is shown as well as improvement on | #7311 Significant improvement over traditionalword alignment techniques is shown as well as improvement on several machine translation tests. |
| measure(ment),15-4-H05-1012,bq | as well as improvement on several <term> | machine translation tests | </term> . <term> Performance </term> of the <term> | #7322 Significant improvement over traditional word alignment techniques is shown as well as improvement on severalmachine translation tests. |
| measure(ment),0-5-H05-1012,bq | <term> machine translation tests </term> . <term> | Performance | </term> of the <term> algorithm </term> is contrasted | #7326 Significant improvement over traditional word alignment techniques is shown as well as improvement on several machine translation tests.Performance of the algorithm is contrasted with human annotation performance. |
| tech,3-5-H05-1012,bq | </term> . <term> Performance </term> of the <term> | algorithm | </term> is contrasted with <term> human annotation | #7329 Performance of thealgorithm is contrasted with human annotation performance. |
| measure(ment),7-5-H05-1012,bq | algorithm </term> is contrasted with <term> | human annotation performance | </term> . This paper presents a <term> phrase-based | #7333 Performance of the algorithm is contrasted withhuman annotation performance. |
