Language modeling with sentence-level mixtures

Publisher Website
Google Scholar
Abstract
This paper introduces a simple mixture language model that attempts to capture long distance constraints in a sentence or paragraph. The model is an m-component mixture of trigram models. The models were constructed using a 5K vocabulary and trained using a 76 million word Wall Street Journal text corpus. Using the BU recognition system, experiments show a 7% improvement in recognition accuracy with the mixture trigram models as compared to using a trigram model.

This publication has 0 references indexed in Scilit: