Large-Scale Topic Detection and Language Model Adaptation.
Abstract
The subject matter of any conversation or document can typically be described as some combination of elemental topics. We have developed a language model adaptation scheme that takes apiece of text, chooses the most similar topic clusters from a set of over 5000 elemental topics, and uses topic specific language models built from the topic clusters to rescore N-best lists. We are able to achieve a 15% reduction in perplexity and a small improvement in word error rate by using this adaptation. We also investigate the use of a topic tree, where the amount of training data for a specific topic can be judiciously increased in cases where the elemental topic cluster has too few word tokens to build a reliably smoothed and representative language model. Our system is able to fine-tune topic adaptation by interpolating models chosen from thousands of topics, allowing for adaptation to unique, previously unseen combinations of subjects.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 1997
- Accession Number
- ADA327553
Entities
People
- Kristie Seymore
- Roni Rosenfeld
Organizations
- Carnegie Mellon University