| 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 on parsing , the techniques described generalize naturally to NLP structures other than parse trees. | |
| tech,0-4-H05-1064,ak | discriminative training criterion </term> . <term> | Training | </term> and <term> decoding </term> with the | #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,1-6-H05-1064,ak | <term> parse reranking </term> . The <term> | model | </term> gives an <term> F-measure improvement | #5528 The model 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 The model learns to automatically make these assignments based on a discriminative training criterion. | |
| 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 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,8-5-H05-1064,ak | </term> . As a case study , we apply the <term> | model | </term> to <term> parse reranking </term> . | #5522 As a case study, we apply the model to parse reranking. |
