A hybrid approach to adaptive statistical language modeling

Publisher Website
Google Scholar
Abstract
We describe our latest attempt at adaptive language modeling. At the heart of our approach is a Maximum Entropy (ME) model, which incorporates many knowledge sources in a consistent manner. The other components are a selective unigram cache, a conditional bigram cache, and a conventional static trigram. We describe the knowledge sources used to build such a model with ARPA's official WSJ corpus, and report on perplexity and word error rate results obtained with it. Then, three different adaptation paradigms are discussed, and an additional experiment, based on AP wire data, is used to compare them.

This publication has 0 references indexed in Scilit: