Concordance

Query H05-1064 20 >
Random sample 20 >
Random sample 20 >
Subparts filter 20 (640.3 per million)

tech,12-1-H05-1064,ak	We describe a new method for the representation of NLP structures within <term> reranking approaches </term> .	#5442 We describe a new method for the representation of NLP structures withinreranking approaches.
model,5-2-H05-1064,ak	We make use of a <term> conditional log-linear model </term> , with <term> hidden variables </term> representing the assignment of <term> lexical items </term> to <term> word clusters </term> or <term> word senses </term> .	#5450 We make use of aconditional log-linear model, with hidden variables representing the assignment of lexical items to word clusters or word senses.
model,10-2-H05-1064,ak	We make use of a <term> conditional log-linear model </term> , with <term> hidden variables </term> representing the assignment of <term> lexical items </term> to <term> word clusters </term> or <term> word senses </term> .	#5455 We make use of a conditional log-linear model, withhidden variables representing the assignment of lexical items to word clusters or word senses.
other,16-2-H05-1064,ak	We make use of a <term> conditional log-linear model </term> , with <term> hidden variables </term> representing the assignment of <term> lexical items </term> to <term> word clusters </term> or <term> word senses </term> .	#5461 We make use of a conditional log-linear model, with hidden variables representing the assignment oflexical items to word clusters or word senses.
model,19-2-H05-1064,ak	We make use of a <term> conditional log-linear model </term> , with <term> hidden variables </term> representing the assignment of <term> lexical items </term> to <term> word clusters </term> or <term> word senses </term> .	#5464 We make use of a conditional log-linear model, with hidden variables representing the assignment of lexical items toword clusters or word senses.
other,22-2-H05-1064,ak	We make use of a <term> conditional log-linear model </term> , with <term> hidden variables </term> representing the assignment of <term> lexical items </term> to <term> word clusters </term> or <term> word senses </term> .	#5467 We make use of a conditional log-linear model, with hidden variables representing the assignment of lexical items to word clusters orword senses.
model,1-3-H05-1064,ak	The <term> model </term> learns to automatically make these assignments based on a <term> discriminative training criterion </term> .	#5471 Themodel learns to automatically make these assignments based on a discriminative training criterion.
model,11-3-H05-1064,ak	The <term> model </term> learns to automatically make these assignments based on a <term> discriminative training criterion </term> .	#5481 The model learns to automatically make these assignments based on adiscriminative training criterion.
tech,0-4-H05-1064,ak	The <term> model </term> learns to automatically make these assignments based on a <term> discriminative training criterion </term> . <term> Training </term> and <term> decoding </term> with the <term> model </term> requires summing over an exponential number of hidden-variable assignments : the required summations can be computed efficiently and exactly using <term> dynamic programming </term> .	#5485 The model learns to automatically make these assignments based on a discriminative training criterion.Training and decoding with the model requires summing over an exponential number of hidden-variable assignments: the required summations can be computed efficiently and exactly using dynamic programming.
tech,2-4-H05-1064,ak	<term> Training </term> and <term> decoding </term> with the <term> model </term> requires summing over an exponential number of hidden-variable assignments : the required summations can be computed efficiently and exactly using <term> dynamic programming </term> .	#5487 Training anddecoding with the model requires summing over an exponential number of hidden-variable assignments: the required summations can be computed efficiently and exactly using dynamic programming.
model,5-4-H05-1064,ak	<term> Training </term> and <term> decoding </term> with the <term> model </term> requires summing over an exponential number of hidden-variable assignments : the required summations can be computed efficiently and exactly using <term> dynamic programming </term> .	#5490 Training and decoding with themodel requires summing over an exponential number of hidden-variable assignments: the required summations can be computed efficiently and exactly using dynamic programming.
tech,26-4-H05-1064,ak	<term> Training </term> and <term> decoding </term> with the <term> model </term> requires summing over an exponential number of hidden-variable assignments : the required summations can be computed efficiently and exactly using <term> dynamic programming </term> .	#5511 Training and decoding with the model requires summing over an exponential number of hidden-variable assignments: the required summations can be computed efficiently and exactly usingdynamic programming.
model,8-5-H05-1064,ak	As a case study , we apply the <term> model </term> to <term> parse reranking </term> .	#5522 As a case study, we apply themodel to parse reranking.
tech,10-5-H05-1064,ak	As a case study , we apply the <term> model </term> to <term> parse reranking </term> .	#5524 As a case study, we apply the model toparse reranking.
model,1-6-H05-1064,ak	The <term> model </term> gives an <term> F-measure improvement </term> of [ ? ] 1.25 % beyond the <term> base parser </term> , and an [ ? ] 0.25 % improvement beyond the <term> Collins ( 2000 ) reranker </term> .	#5528 Themodel gives an F-measure improvement of [?] 1.25% beyond the base parser, and an [?] 0.25% improvement beyond the Collins (2000) reranker.
measure(ment),4-6-H05-1064,ak	The <term> model </term> gives an <term> F-measure improvement </term> of [ ? ] 1.25 % beyond the <term> base parser </term> , and an [ ? ] 0.25 % improvement beyond the <term> Collins ( 2000 ) reranker </term> .	#5531 The model gives anF-measure improvement of [?] 1.25% beyond the base parser, and an [?] 0.25% improvement beyond the Collins (2000) reranker.
tech,14-6-H05-1064,ak	The <term> model </term> gives an <term> F-measure improvement </term> of [ ? ] 1.25 % beyond the <term> base parser </term> , and an [ ? ] 0.25 % improvement beyond the <term> Collins ( 2000 ) reranker </term> .	#5541 The model gives an F-measure improvement of [?] 1.25% beyond thebase parser, and an [?] 0.25% improvement beyond the Collins (2000) reranker.
tool,27-6-H05-1064,ak	The <term> model </term> gives an <term> F-measure improvement </term> of [ ? ] 1.25 % beyond the <term> base parser </term> , and an [ ? ] 0.25 % improvement beyond the <term> Collins ( 2000 ) reranker </term> .	#5554 The model gives an F-measure improvement of [?] 1.25% beyond the base parser, and an [?] 0.25% improvement beyond theCollins ( 2000 ) reranker.
tech,6-7-H05-1064,ak	Although our experiments are focused on <term> parsing </term> , the techniques described generalize naturally to NLP structures other than <term> parse trees </term> .	#5566 Although our experiments are focused onparsing, the techniques described generalize naturally to NLP structures other than parse trees.
other,18-7-H05-1064,ak	Although our experiments are focused on <term> parsing </term> , the techniques described generalize naturally to NLP structures other than <term> parse trees </term> .	#5578 Although our experiments are focused on parsing, the techniques described generalize naturally to NLP structures other thanparse trees.


	in Help