Human languages are full of ambiguous words. For example, the word "bat" can mean a nocturnal animal, a sports apparatus, or a blink of an eye. Humans seem to effortlessly select the appropriate meaning when hearing ambiguous words in context. But this process, known as Word Sense Disambiguation (WSD), has proved difficult for the computer to emulate. This problem was one of the first to be identified in Natural Language Processing and has been intensively studied in recent years. Common applications include internet searches and the translation of human languages.
This book provides descriptions of novel research as well as an overview of the field of WSD, with accounts of previous approaches and methodological issues. The work described here is closely related to the field of lexicography -- the process of creating dictionaries.
The author presents a description and an evaluation of a practical computer system that has been found to produce extremely accurate word-disambiguation decisions in English. Among the information utilized by this system is the grammatical behaviors of words, the topics of the texts in which they are used, and definitions found in the dictionary. A central thesis of this book is that, while the combination of these knowledge sources is more effective than any one used alone, these sources are, to some degree, independent.
To order this book, contact:
The University of Chicago Press.
Call their toll free order number 1-800-621-2736 (U.S. & Canada only) or order online at http://www.press.uchicago.edu/ (use the search feature to locate the book, then order).