| other,9-3-N03-1017,ak | results , which hold for all examined <term> | language pairs | </term> , suggest that the highest levels | #2598 Our empirical results, which hold for all examinedlanguage pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. | |
| model,21-2-N03-1017,ak | phrase-based models </term> outperform <term> | word-based models | </term> . Our empirical results , which hold | #2586 Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models outperformword-based models. | |
| other,39-3-N03-1017,ak | and <term> lexical weighting </term> of <term> | phrase translations | </term> . Surprisingly , learning <term> phrases | #2628 Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting ofphrase translations. | |
| model,21-1-N03-1017,ak | compare several , previously proposed <term> | phrase-based translation models | </term> . Within our framework , we carry | #2561 We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposedphrase-based translation models. | |
| model,4-1-N03-1017,ak | </term> of 54.55 % ) . We propose a new <term> | phrase-based translation model | </term> and <term> decoding algorithm </term> | #2544 We propose a newphrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. | |
| other,7-4-N03-1017,ak | <term> phrases </term> longer than three <term> | words | </term> and learning <term> phrases </term> from | #2638 Surprisingly, learning phrases longer than threewords and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance. | |
| lr,33-3-N03-1017,ak | <term> phrase translations </term> from <term> | word-based alignments | </term> and <term> lexical weighting </term> | #2622 Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations fromword-based alignments and lexical weighting of phrase translations. | |
| other,2-5-N03-1017,ak | impact on performance . Learning only <term> | syntactically motivated phrases | </term> degrades the performance of our systems | #2658 Learning onlysyntactically motivated phrases degrades the performance of our systems. | |
| model,12-4-N03-1017,ak | and learning <term> phrases </term> from <term> | high-accuracy word-level alignment models | </term> does not have a strong impact on | #2643 Surprisingly, learning phrases longer than three words and learning phrases fromhigh-accuracy word-level alignment models does not have a strong impact on performance. | |
| other,10-4-N03-1017,ak | three <term> words </term> and learning <term> | phrases | </term> from <term> high-accuracy word-level | #2641 Surprisingly, learning phrases longer than three words and learningphrases from high-accuracy word-level alignment models does not have a strong impact on performance. | |
| other,30-3-N03-1017,ak | : <term> heuristic learning </term> of <term> | phrase translations | </term> from <term> word-based alignments </term> | #2619 Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning ofphrase translations from word-based alignments and lexical weighting of phrase translations. | |
| other,3-4-N03-1017,ak | translations </term> . Surprisingly , learning <term> | phrases | </term> longer than three <term> words </term> | #2634 Surprisingly, learningphrases longer than three words and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance. | |
| tech,27-3-N03-1017,ak | through relatively simple means : <term> | heuristic learning | </term> of <term> phrase translations </term> | #2616 Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means:heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. | |
| tech,36-3-N03-1017,ak | <term> word-based alignments </term> and <term> | lexical weighting | </term> of <term> phrase translations </term> | #2625 Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments andlexical weighting of phrase translations. | |
| model,18-2-N03-1017,ak | understand better and explain why <term> | phrase-based models | </term> outperform <term> word-based models | #2583 Within our framework, we carry out a large number of experiments to understand better and explain whyphrase-based models outperform word-based models. | |
| tech,8-1-N03-1017,ak | phrase-based translation model </term> and <term> | decoding algorithm | </term> that enables us to evaluate and compare | #2548 We propose a new phrase-based translation model anddecoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. |
