Concordance

Query P05-1034 21 >
Shuffle 21 (979.1 per million)

other,21-1-P05-1034,bq	language </term> with recent advances in <term>	phrasal translation	</term> . This <term> method </term> requires	#9222 We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances inphrasal translation.
tech,14-2-P05-1034,bq	<term> word segmentation </term> and an <term>	unsupervised word alignment component	</term> . We align a <term> parallel corpus	#9239 This method requires a source-language dependency parser, target language word segmentation and anunsupervised word alignment component.
lr,3-3-P05-1034,bq	alignment component </term> . We align a <term>	parallel corpus	</term> , project the <term> source dependency	#9247 We align aparallel corpus, project the source dependency parse onto the target sentence, extract dependency treelet translation pairs, and train a tree-based ordering model.
model,25-3-P05-1034,bq	translation pairs </term> , and train a <term>	tree-based ordering model	</term> . We describe an efficient <term> decoder	#9269 We align a parallel corpus, project the source dependency parse onto the target sentence, extract dependency treelet translation pairs, and train atree-based ordering model.
other,17-3-P05-1034,bq	target <term> sentence </term> , extract <term>	dependency treelet translation pairs	</term> , and train a <term> tree-based ordering	#9261 We align a parallel corpus, project the source dependency parse onto the target sentence, extractdependency treelet translation pairs, and train a tree-based ordering model.
tech,4-4-P05-1034,bq	model </term> . We describe an efficient <term>	decoder	</term> and show that using these <term> tree-based	#9277 We describe an efficientdecoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.
model,10-4-P05-1034,bq	decoder </term> and show that using these <term>	tree-based models	</term> in combination with conventional <term>	#9283 We describe an efficient decoder and show that using thesetree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.
tech,6-1-P05-1034,bq	describe a novel <term> approach </term> to <term>	statistical machine translation	</term> that combines <term> syntactic information	#9207 We describe a novel approach tostatistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation.
other,4-2-P05-1034,bq	This <term> method </term> requires a <term>	source-language	</term><term> dependency parser </term> , <term>	#9229 This method requires asource-language dependency parser, target language word segmentation and an unsupervised word alignment component.
tech,10-2-P05-1034,bq	</term> , <term> target language </term><term>	word segmentation	</term> and an <term> unsupervised word alignment	#9235 This method requires a source-language dependency parser, target languageword segmentation and an unsupervised word alignment component.
other,15-1-P05-1034,bq	syntactic information </term> in the <term>	source language	</term> with recent advances in <term> phrasal	#9216 We describe a novel approach to statistical machine translation that combines syntactic information in thesource language with recent advances in phrasal translation.
tech,5-2-P05-1034,bq	requires a <term> source-language </term><term>	dependency parser	</term> , <term> target language </term><term>	#9230 This method requires a source-languagedependency parser, target language word segmentation and an unsupervised word alignment component.
tech,27-4-P05-1034,bq	approach that incorporates the power of <term>	phrasal SMT	</term> with the linguistic generality available	#9300 We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power ofphrasal SMT with the linguistic generality available in a parser.
other,11-1-P05-1034,bq	machine translation </term> that combines <term>	syntactic information	</term> in the <term> source language </term>	#9212 We describe a novel approach to statistical machine translation that combinessyntactic information in the source language with recent advances in phrasal translation.
tech,4-1-P05-1034,bq	quality </term> . We describe a novel <term>	approach	</term> to <term> statistical machine translation	#9205 We describe a novelapproach to statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation.
other,8-3-P05-1034,bq	parallel corpus </term> , project the <term>	source dependency parse	</term> onto the target <term> sentence </term>	#9252 We align a parallel corpus, project thesource dependency parse onto the target sentence, extract dependency treelet translation pairs, and train a tree-based ordering model.
tech,36-4-P05-1034,bq	linguistic generality available in a <term>	parser	</term> . We directly investigate a subject	#9309 We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in aparser.
model,16-4-P05-1034,bq	</term> in combination with conventional <term>	SMT models	</term> provides a promising approach that	#9289 We describe an efficient decoder and show that using these tree-based models in combination with conventionalSMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser.
other,14-3-P05-1034,bq	dependency parse </term> onto the target <term>	sentence	</term> , extract <term> dependency treelet	#9258 We align a parallel corpus, project the source dependency parse onto the targetsentence, extract dependency treelet translation pairs, and train a tree-based ordering model.
other,8-2-P05-1034,bq	</term><term> dependency parser </term> , <term>	target language	</term><term> word segmentation </term> and	#9233 This method requires a source-language dependency parser,target language word segmentation and an unsupervised word alignment component.


	in Help