- About this Journal
- Abstracting and Indexing
- Aims and Scope
- Article Processing Charges
- Articles in Press
- Author Guidelines
- Bibliographic Information
- Citations to this Journal
- Contact Information
- Editorial Board
- Editorial Workflow
- Free eTOC Alerts
- Publication Ethics
- Submit a Manuscript
- Table of Contents
ISRN Artificial Intelligence
Volume 2012 (2012), Article ID 918362, 6 pages
doi:10.5402/2012/918362
A Smart Proofreader for All Natural Languages: Achieving Semantic Understanding by Majority Vote
1Department of Economy, Informatics and Social Science, Molde University College, P.O. Box 2110, 6402 Molde, Norway
2Department of Informatics, University of Bergen, 5020 Bergen, Norway
Received 27 October 2011; Accepted 17 November 2011
Academic Editor: C. Gentile
Copyright © 2012 Kai A. Olsen. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The language tools offered in common word processors use dictionaries and simple grammatical rules. They cannot detect errors such as a wrong preposition, interchanged words, or typos that result in a dictionary word. However, by comparing the user's text to a large repository, it is possible to detect many of these errors and also to suggest alternatives. By looking at full sentences, it is often possible to get the correct context. This is important in detecting errors and in order to offer valuable suggestions. These ideas have been implemented in a prototype system. We present examples in English and Norwegian, but the method, that of following a “majority vote,” can be applied to any written language.