Second International Conference on Spoken Language Processing (ICSLP'92)
Banff, Alberta, Canada
The construction of a speech understanding application requires a method for extracting language models of appropriate size and perplexity from the application grammar. We describe a method for approximating context-free grammars by finite-state models with a range of sizes and perplexities and present experimental results of its application to a variety of grammars, including a fairly large grammar for a spoken-language translation application.
Bibliographic reference. Pereira, Fernando / Roe, David (1992): "Empirical properties of finite state approximations for phrase structure grammars", In ICSLP-1992, 261-264.