Improving Language Model Size Reduction using Better Pruning
by
Criteria Jianfeng Gao
,
Jianfeng Gao
| Venue: | In Proc. of ACL |
| Citations: | 2 - 0 self |
BibTeX
@INPROCEEDINGS{Gao_improvinglanguage,
author = {Criteria Jianfeng Gao and Jianfeng Gao},
title = {Improving Language Model Size Reduction using Better Pruning},
booktitle = {In Proc. of ACL},
year = {},
pages = {176--182}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Reducing language model (LM) size is a critical issue when applying a LM to realistic applications which have memory constraints. In this paper, three measures are studied for the purpose of LM pruning. They are probability, rank, and entropy. We evaluated the performance of the three pruning criteria in a real application of Chinese text input in terms of character error rate (CER). We first present an empirical comparison, showing that rank performs the best in most cases.
Citations
| 302 | Self-organized language modeling for speech recognition - Jelinek - 1990 |
| 201 | A maximum entropy approach to adaptive statistical language modelling - Rosenfeld - 1996 |
| 40 | Toward a unified approach to statistical language modeling for Chinese - Gao, Goodman, et al. - 2002 |
| 7 | Improved language modelling through better language model evaluation measures. Computer Speech and Language - Clarkson, Robinson - 2001 |
| 6 | XXXX) Distribution-Based Pruning of Backoff Language Models - Gao, Lee - 1987 |
| 6 | Estimation of probabilities from sparse data for other language component of a speech recognizer - Katz - 1987 |
