Abstract
Nowadays, newly coined terms or new usage of existing terms are flourishing due to the prevailing trends of social network sites and Internet forums. Therefore, there is a pressing need for updated and reliable definitions. However, the traditional manually edited dictionaries had fallen behind in providing neologisms' definitions in time. In this paper, we present a method for automatically finding Chinese neologism definitions on the Web. In our approach, we use lexical patterns to bias the search engine towards retrieving snippets containing the definition of the given term. We use Wikipedia as training data to build a definition classifier without human annotated training data. Furthermore, we cluster the definition candidates by their meanings, in order to distinguish existing and new meanings. In our experiments, we applied the proposed system to find definitions for about 150 Chinese neologisms on the Web. The experimental results show that the proposed methods are reasonably accurate providing an efficient way to mine definitions on the Web.