Loading...
Please wait, while we are loading the content...
Similar Documents
A Maximum Entropy Approach to Adaptive Statistical Language Modeling (1996)
| Content Provider | CiteSeerX |
|---|---|
| Author | Rosenfeld, Ronald |
| Abstract | An adaptive statistical language model is described, which successfully integrates long distance linguistic information with other knowledge sources. Most existing statistical language models exploit only the immediate history of a text. To extract information from further back in the document's history, we propose and use trigger pairs as the basic information bearing elements. This allows the model to adapt its expectations to the topic of discourse. Next, statistical evidence from multiple sources must be combined. Traditionally, |
| File Format | |
| Journal | COMPUTER, SPEECH AND LANGUAGE |
| Publisher Date | 1996-01-01 |
| Access Restriction | Open |
| Subject Keyword | Adaptive Statistical Language Model Immediate History Basic Information Bearing Element Long Distance Linguistic Information Statistical Language Model Statistical Evidence Adaptive Statistical Language Modeling Maximum Entropy Approach |
| Content Type | Text |
