Title:
Class-based_n-gram_models_of_natural_language
Download
Description: We address the problem of predicting a word from previous words in a sample of text. In particular, we discuss n-gram models based on classes of words. We also discuss several statistical algorithmsfor assigning words to classes based on the frequency of their co- occurrence with other words. Wefind that we are able to extract classes that have the flavor of either syntactically based groupingsor semantically based groupings, depending on the nature of the underlying statistics.
File list (Check if you may need any files):
Class-based n-gram models of natural language.pdf
