| W11-0809 | finitestate lexical analysis and a | CRF decoding | using weighted finite-state transducer |
| W11-0809 | finite-state lexical analysis and a | CRF decoding | using weighted finitestate transducer |
| D09-1134 | pλ ( y | x ) as in standard | CRF decoding | , ignoring virtual evidence . |
| W06-2918 | more complex than for standard | CRF decoding | . In order to use a LOP for decoding |
| N12-1008 | maximization is achieved through standard | CRF decoding | . For the local potentials , |
| P10-2051 | to stop performing the second | CRF decoding | . Suppose we have a list of segmentation |
| P10-2051 | and we are performing the 2nd | CRF decoding | starting from A1 . Up to Ak , |
| P10-2051 | segmentation step and 10 nbest | CRF decoding | in the second CRF . Is it really |
| P10-2051 | process we have to perform n-best | CRF decoding | in the segmentation step and |
| P10-2051 | that , even performing the 2nd | CRF decoding | for all the remaining segmentations |
| P05-1002 | increases . 3.2 Error-correcting | CRF decoding | While training of error-correcting |
