| tech,4-1-H05-1095,ak | trees </term> . This paper presents a <term> | phrase-based statistical machine translation method | </term> , based on <term> non-contiguous phrases | #5585 This paper presents aphrase-based statistical machine translation method, based on non-contiguous phrases, i.e. phrases with gaps. | |
| other,12-1-H05-1095,ak | translation method </term> , based on <term> | non-contiguous phrases | </term> , i.e. <term> phrases </term> with gaps | #5593 This paper presents a phrase-based statistical machine translation method, based onnon-contiguous phrases, i.e. phrases with gaps. | |
| other,16-1-H05-1095,ak | non-contiguous phrases </term> , i.e. <term> | phrases | </term> with gaps . A method for producing | #5597 This paper presents a phrase-based statistical machine translation method, based on non-contiguous phrases, i.e.phrases with gaps. | |
| other,5-2-H05-1095,ak | gaps . A method for producing such <term> | phrases | </term> from a <term> word-aligned corpora </term> | #5606 A method for producing suchphrases from a word-aligned corpora is proposed. | |
| lr,8-2-H05-1095,ak | producing such <term> phrases </term> from a <term> | word-aligned corpora | </term> is proposed . A <term> statistical | #5609 A method for producing such phrases from aword-aligned corpora is proposed. | |
| model,1-3-H05-1095,ak | word-aligned corpora </term> is proposed . A <term> | statistical translation model | </term> is also presented that deals such | #5615 Astatistical translation model is also presented that deals such phrases, as well as a training method based on the maximization of translation accuracy, as measured with the NIST evaluation metric. | |
| other,10-3-H05-1095,ak | </term> is also presented that deals such <term> | phrases | </term> , as well as a <term> training method | #5624 A statistical translation model is also presented that deals suchphrases, as well as a training method based on the maximization of translation accuracy, as measured with the NIST evaluation metric. | |
| tech,16-3-H05-1095,ak | <term> phrases </term> , as well as a <term> | training method | </term> based on the <term> maximization </term> | #5630 A statistical translation model is also presented that deals such phrases, as well as atraining method based on the maximization of translation accuracy, as measured with the NIST evaluation metric. | |
| tech,21-3-H05-1095,ak | training method </term> based on the <term> | maximization | </term> of <term> translation accuracy </term> | #5635 A statistical translation model is also presented that deals such phrases, as well as a training method based on themaximization of translation accuracy, as measured with the NIST evaluation metric. | |
| measure(ment),23-3-H05-1095,ak | on the <term> maximization </term> of <term> | translation accuracy | </term> , as measured with the <term> NIST | #5637 A statistical translation model is also presented that deals such phrases, as well as a training method based on the maximization oftranslation accuracy, as measured with the NIST evaluation metric. | |
| measure(ment),30-3-H05-1095,ak | accuracy </term> , as measured with the <term> | NIST evaluation metric | </term> . <term> Translations </term> are produced | #5644 A statistical translation model is also presented that deals such phrases, as well as a training method based on the maximization of translation accuracy, as measured with theNIST evaluation metric. | |
| other,0-4-H05-1095,ak | <term> NIST evaluation metric </term> . <term> | Translations | </term> are produced by means of a <term> beam-search | #5648 A statistical translation model is also presented that deals such phrases, as well as a training method based on the maximization of translation accuracy, as measured with the NIST evaluation metric.Translations are produced by means of a beam-search decoder. | |
| tech,7-4-H05-1095,ak | Translations </term> are produced by means of a <term> | beam-search decoder | </term> . Experimental results are presented | #5655 Translations are produced by means of abeam-search decoder. | |
| lr,17-5-H05-1095,ak | allows to better generalize from the <term> | training data | </term> . This paper investigates some <term> | #5675 Experimental results are presented, that demonstrate how the proposed method allows to better generalize from thetraining data. |
