7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

A Maximum Entropy Semantic Parser Using Word Classes

Norbert Pfannerer

SAIL LABS Technology AG, Austria

This paper describes the parser that is used in the Sail Labs Conversational System, which is a spoken dialog system. This parser is a fully statistical, semantic parser. The probability model of the parser is based on the principle of maximum entropy. The maximum entropy framework allows to combine the available information in a fully automatic way, but the training of maximum entropy models is time consuming. Since the parser needs to be retrained when its vocabulary changes, a straightforward application of this model cannot realistically be used in a dialog system. To solve this problem, words can be combined to classes, and the classes can be used instead of the words for the training of the parser. At runtime, words can be added to the classes at no cost.


Full Paper

Bibliographic reference.  Pfannerer, Norbert (2002): "A maximum entropy semantic parser using word classes", In ICSLP-2002, 617-620.