Measuring Similarities between Technical Terms Based on Wikipedia

Measuring similarities between terms is useful for semantic information processing such as query expansion and WSD (Word Sense Disambiguation). This study aims at identifying technologies closely related to emerging technologies. Thus, we propose a hybrid method using both category and internal link information in Wikipedia, which is the largest database that everyone can share and edit its contents. Comparative experimental results with a state-of-the art WLM (Wikipedia Link-based Measure) show that this proposed method works better than each single method.