Limits on the Application of Frequency-Based Language Models to OCR

Abstract

Although large language models are used in speech recognition and machine translation applications, OCR systems are "far behind" in their use of language models. The reason for this is not the laggardness of the OCR community, but the fact that, at high accuracies, a frequency-based language model can do more damage than good, unless carefully applied. This paper presents an analysis of this discrepancy with the help of the Google Books n-gram Corpus, and concludes that noisy-channel models that closely model the underlying classifier and segmentation errors are required.