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