عنوان مقاله [English]
The rapid growth of electronic information in the present age has resulted in creating various types of bibliographic networks. Accessing electronic information requires applying effective ways to identify and organic the important clues to the content of a document. Therefore OCLC as the best known and most huge bibliographic network in the world, has created an indexing system known as Wordsmith to provide facilities for rapid and effective access to information. This systems major activity is to distinguish concepts, words and key phrases in machine-readable text on the basis of natural language processing. In order to accomplish this activity, Wordsmith is taking advantage of computational and semantic linguistic .theories-that is emphasized in natural language processing. It also uses information science theories and statistical models to implement its mission.