Class Phrase Models for Language Modeling

October 1996

Class Phrase Models for Language Modeling

Authors:

Klaus Ries, Finn Dag Buo, and Alex Waibel

Abstract:

Previous attempts to automatically determine multi-words as the basic unit for language modeling have been successful for extending bigram models to improve the perplexity of the language model and/or the word accuracy of the speech decoder. However, none of these techniques gave improvements over the trigram model so far, except for the rather controlled ATIS task (McCandless & Glass, 1994). We therefore propose an algorithm that minimizes the perplexity of a bigram model directly. The new algorithm is able to reduce the trigram perplexity and also achieves word accuracy improvements in the Verbmobil task. It is the natural counterpart of successful word classification algorithms for language modeling that minimize the leaving-one-out bigram perplexity. We also give some details on the usage of class-finding techniques and m-gram models, which can be crucial to successful applications of this technique.
@conference{Ries-1996-14225,
author = {Klaus Ries And Finn Dag Buo And Alex Waibel},
title = {Class Phrase Models for Language Modeling},
booktitle = {Proceedings of 4th International Conference on Spoken Language Processing (ICSLP '96)},
year = {1996},
month = {October},
volume = {1},
pages = {398 - 401},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.