Discriminative language modeling with conditional random fields and the perceptron algorithm (2004)
| Venue: | In Proc. ACL |
| Citations: | 41 - 4 self |
BibTeX
@INPROCEEDINGS{Roark04discriminativelanguage,
author = {Brian Roark and Murat Saraclar},
title = {Discriminative language modeling with conditional random fields and the perceptron algorithm},
booktitle = {In Proc. ACL},
year = {2004},
pages = {47--54}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a method based on conditional random fields (CRFs). The models are encoded as deterministic weighted finite state automata, and are applied by intersecting the automata with word-lattices that are the output from a baseline recognizer. The perceptron algorithm has the benefit of automatically selecting a relatively small feature set in just a couple of passes over the training data. However, using the feature set output from the perceptron algorithm (initialized with their weights), CRF training provides an additional 0.5 % reduction in word error rate, for a total 1.8 % absolute reduction from the baseline of 39.2%. 1
