Better Language Models with Model Merging

DMCA

Better Language Models with Model Merging (1996)

Cached

Download Links

Other Repositories/Bibliography

CiteULike
DBLP

by Thorsten Brants

Venue:	IN PROC. OF THE CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP-96
Citations:	3 - 0 self

BibTeX

@INPROCEEDINGS{Brants96betterlanguage,
    author = {Thorsten Brants},
    title = {Better Language Models with Model Merging},
    booktitle = {IN PROC. OF THE CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP-96},
    year = {1996},
    publisher = {}
}

OpenURL

Abstract

This paper investigates model merging, a technique for deriving Markov models from text or speech corpora. Models are derived by starting with a large and specific model and by successively combining states to build smaller and more general models. We present methods to reduce the time complexity of the algorithm and report on experiments on deriving language models for a speech recognition task. The experiments show the advantage of model merging over the standard bigram approach. The merged model assigns a lower perplexity to the test set and uses considerably fewer states.

Keyphrases

better language model test set language model specific model merged model standard bigram approach model merging present method speech corpus general model time complexity speech recognition task markov model

DMCA