A Novel Approach to Measure Semantic Similarity Between Words Using Web Search Engine

Semantic similarity measures play important roles in Information Retrieval (IR) and Natural Language Processing (NLP). Accurately measuring the semantic similarity between two words (or entities) is an important problem in web mining. Web mining application such as community mining, relation detection, and entity disambiguation requires the ability to accurately measure the semantic similarity between concepts or entities remains a challenging task. The authors propose a novel approach to estimate semantic similarity that uses the information available on the Web to measure similarity between words or entities. The proposed method exploits page counts and text snippets returned by a Web search engine.