Language Modeling With Sentence-Level Mixtures

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 Wail Street Journal text c...

Full description

Saved in:
Bibliographic Details
Main Authors: Iyer, Rukmini, Ostendorf, Mari, Rohlicek, J R
Format: Report
Language:English
Subjects:
ACCURACY
Linguistics
SPEECH RECOGNITION
WORDS(LANGUAGE)
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 Wail 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.