Abstract | ||
---|---|---|
Current alternatives for language modeling are statistical techniques based on large amounts of training data, and hand-crafted context-free or finite-state grammars that are difficult to build and maintain. One way to address the problems of the grammar-based approach is to compile recognition grammars from grammars written in a more expressive formalism. While theoretically straight-forward, the compilation process can exceed memory and time bounds, and might not always result in accurate and efficient speech recognition. We will describe and evaluate two approaches to this compilation problem. We will also describe and evaluate additional techniques to reduce the structural ambiguity of the language model. |
Year | DOI | Venue |
---|---|---|
2001 | 10.3115/1073012.1073034 | ACL |
Keywords | Field | DocType |
current alternative,language model,practical issue,unification grammar,efficient speech recognition,compilation process,recognition grammar,finite-state grammar,expressive formalism,additional technique,language modeling,compilation problem,speech recognition | Rule-based machine translation,Programming language,Computer science,Artificial intelligence,Natural language processing,Ambiguity,Language model,L-attributed grammar,Extended Affix Grammar,Unification,Compiler,Speech recognition,Grammar | Conference |
Volume | Citations | PageRank |
P01-1 | 10 | 1.24 |
References | Authors | |
14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
John Dowding | 1 | 71 | 17.10 |
Beth Ann Hockey | 2 | 212 | 36.35 |
Jean Mark Gawron | 3 | 187 | 51.92 |
Christopher Culy | 4 | 40 | 6.84 |