A Wikipedia-based English-Language Reference and Teaching Tool

This paper describes software under development that automatically extracts information from corpora that can be useful for language learners and language researchers. This software provides users with lists of words (extracted from several large corpora) that are frequently used in various English genres. In addition, the software extracts the following types of information from Wikipedia: 1) word frequency: users can view lists of frequent words, 2) word forms: users can view different morphological forms of target words, 3) part of speech information: users can view the part of speech distribution of target words, and 3) example paragraphs: users can view sample paragraphs containing different usages of target words.