Data Compression White Papers
Comparison of Width-wise and Length-wise Language Model Compression
Overview
In this paper we investigate the extent to which Katz back-off language models can be compressed through a combination of parameter quantization (width-wise compression) and parameter pruning
(length-wise compression) methods while preserving performance.
We compare the compression and performance that is achieved using entropy-based pruning against that achieved using only parameter quantization. We then compare combinations of both methods. It is
shown that a broadcast news language model can be compressed by up to 83% to only 12.6Mb with no loss in performance on a broadcast news task. Compressing the language model further by quantization to 10.3Mb resulted in only a 0.4% degradation in word error rate which is better than can be achieved through entropy-based pruning alone.
| Publisher | Mitsubishi Electric Research Laboratories (MERL) | File Format | HTML & PDF |
|---|---|---|---|
| Date Published | December 2001 | Downloads | 103 |
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful?
White Paper RSS
Download
Register
