Paper: Randomized Language Models via Perfect Hash Functions

ACL ID P08-1058
Title Randomized Language Models via Perfect Hash Functions
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

We propose a succinct randomized language model which employs a perfect hash func- tion to encode fingerprints of n-grams and theirassociatedprobabilities, backoffweights, or other parameters. The scheme can repre- sent any standard n-gram model and is easily combined with existing model reduction tech- niques such as entropy-pruning. We demon- strate the space-savings of the scheme via ma- chine translation experiments within a dis- tributed language modeling framework.