Concordance

Query N03-1017 17 >
Multilevel Sort 17 (792.6 per million)

lr,33-3-N03-1017,bq	<term> phrase translations </term> from <term>	word-based alignments	</term> and <term> lexical weighting </term>	#2621 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.
model,12-4-N03-1017,bq	and learning <term> phrases </term> from <term>	high-accuracy word-level alignment models	</term> does not have a strong impact on	#2642 Surprisingly, learning phrases longer than three words and learning phrases fromhigh-accuracy word-level alignment models does not have a strong impact on performance.
model,18-2-N03-1017,bq	understand better and explain why <term>	phrase-based models	</term> outperform <term> word-based models	#2582 Within our framework, we carry out a large number of experiments to understand better and explain whyphrase-based models outperform word-based models.
model,21-1-N03-1017,bq	compare several , previously proposed <term>	phrase-based translation models	</term> . Within our framework , we carry	#2560 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,21-2-N03-1017,bq	phrase-based models </term> outperform <term>	word-based models	</term> . Our empirical results , which hold	#2585 Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models outperformword-based models.
model,4-1-N03-1017,bq	</term> of 54.55 % ) . We propose a new <term>	phrase-based translation model	</term> and <term> decoding algorithm </term>	#2543 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,10-4-N03-1017,bq	three <term> words </term> and learning <term>	phrases	</term> from <term> high-accuracy word-level	#2640 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,2-5-N03-1017,bq	impact on performance . Learning only <term>	syntactically motivated phrases	</term> degrades the performance of our <term>	#2657 Learning onlysyntactically motivated phrases degrades the performance of our systems.
other,3-4-N03-1017,bq	translations </term> . Surprisingly , learning <term>	phrases	</term> longer than three <term> words </term>	#2633 Surprisingly, learningphrases longer than three words and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance.
other,30-3-N03-1017,bq	: <term> heuristic learning </term> of <term>	phrase translations	</term> from <term> word-based alignments </term>	#2618 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,39-3-N03-1017,bq	and <term> lexical weighting </term> of <term>	phrase translations	</term> . Surprisingly , learning <term> phrases	#2627 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.
other,7-4-N03-1017,bq	<term> phrases </term> longer than three <term>	words	</term> and learning <term> phrases </term> from	#2637 Surprisingly, learning phrases longer than threewords and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance.
other,9-3-N03-1017,bq	results , which hold for all examined <term>	language pairs	</term> , suggest that the highest levels	#2597 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.
tech,10-5-N03-1017,bq	</term> degrades the performance of our <term>	systems	</term> . In this paper , we introduce a <term>	#2665 Learning only syntactically motivated phrases degrades the performance of oursystems.
tech,27-3-N03-1017,bq	through relatively simple means : <term>	heuristic learning	</term> of <term> phrase translations </term>	#2615 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,bq	<term> word-based alignments </term> and <term>	lexical weighting	</term> of <term> phrase translations </term>	#2624 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.
tech,8-1-N03-1017,bq	phrase-based translation model </term> and <term>	decoding algorithm	</term> that enables us to evaluate and compare	#2547 We propose a new phrase-based translation model anddecoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models.


	in Help