Integrating history-length interpolation and classes in language modeling

by Hinrich Schütze

Datum	Value	Source
TITLE	Integrating history-length interpolation and classes in language modeling	SVM HeaderParse 0.2
AUTHOR NAME	Hinrich Schütze	SVM HeaderParse 0.2
AUTHOR AFFIL	Institute for NLP; University of Stuttgart	SVM HeaderParse 0.2
AUTHOR ADDR	Germany	SVM HeaderParse 0.2
ABSTRACT	Building on earlier work that integrates different factors in language modeling, we view (i) backing off to a shorter history and (ii) class-based generalization as two complementary mechanisms of using a larger equivalence class for prediction when the default equivalence class is too small for reliable estimation. This view entails that the classes in a language model should be learned from rare events only and should be preferably applied to rare events. We construct such a model and show that both training on rare events and preferable application to rare events improve perplexity when compared to a simple direct interpolation of class-based with standard language models. 1	SVM HeaderParse 0.2
CITATIONS	27 found	ParsCit 1.0