Relatedness and Its Application in Natural Language Processing

Lexical Semantic Relatedness and Its Application in Natural Language Processing Alexander Budanitsky Department of Computer Science University of Toronto August 1999 A great variety of Natural Language Processing tasks, from word sense disambiguation to text summarization to speech recognition, rely heavily on the ability to measure semantic relatedness or distance between words of a natural language. This report is a comprehensive study of recent computational methods of measuring lexical semantic relatedness. A survey of methods, as well as their applications, is presented, and the question of evaluation is addressed both theoretically and experimentally. Application to the speci c task of intelligent spelling checking is discussed in detail: the design of a prototype system for the detection and correction of malapropisms (words that are similar in spelling or sound to, but quite di erent in meaning from, intended words) is described, and results of experiments on using various measures as plug-ins are considered. Suggestions for research directions in the areas of measuring semantic relatedness and intelligent spelling checking are o ered.