| D08-1006 | reason , the whole - sentence | maximum-entropy | model was proposed in ( Rosenfeld |
| C00-1082 | the 152 1 ) atterns fl ` om the | maximum-entropy | method to establish the level |
| A00-2018 | selection , as in Ratnaparkhi 's | maximum-entropy | parser -LSB- 17 -RSB- . While |
| D08-1035 | phrases are used as a feature in a | maximum-entropy | classifier for conversation disentanglement |
| C00-1030 | ( Nobata et al. , 1.999 ) and | maximum-entropy | . The maximum entropy model shown |
| A00-2018 | observe that if we were to use a | maximum-entropy | approach but run iterative scaling |
| D09-1160 | model ( LLM ) , or also known as | maximum-entropy | model ( Berger et al. , 1996 |
| D08-1107 | prepositions and adverbs . " It uses a | maximum-entropy | approach to handle information |
| A00-2018 | without smooth - ing . In a pure | maximum-entropy | model this is done by feature |
| D10-1033 | these and use them as input to a | maximum-entropy | classifier ( separate from the |
| D10-1044 | and Marcu ( 2006 ) , who used a | maximum-entropy | model with latent variables to |
| D08-1006 | overview of the whole-sentence | maximum-entropy | model and of self-supervised |
| A00-2018 | on-line computational problem for | maximum-entropy | models , this simplifies the |
| D10-1033 | and " bad " , use a " mixed " | maximum-entropy | MD model whose training data |
| C00-1082 | nmnber of features used in the | maximum-entropy | method is 152 , which is obtained |
| D10-1033 | Zitouni and Florian , 2009 ) . The | maximum-entropy | model is trained using the sequential |
| C00-1082 | a. 2 Maximum-entropy method The | maximum-entropy | method is useful with sparse |
| A00-2018 | values picked so that , when the | maximum-entropy | equation is expressed in the |
| D10-1033 | language-identification classifier and the | maximum-entropy | " how-English " classifier are |
| D10-1033 | . Our goal is to select among | maximum-entropy | MD classifiers trained separately |
