主催: 一般社団法人 人工知能学会
会議名: 2013年度人工知能学会全国大会(第27回)
回次: 27
開催地: 富山県富山市 富山国際会議場
開催日: 2013/06/04 - 2013/06/07
Chinese words which share the same character may carry related but different meanings, e.g., “花錢”, “花費” , “花草”, “花木”. The semantics of these words form two clusters: {“花錢”, “花費”} and {“花草”, “花木”}. Differentiating and clustering senses of these related words are related to the problem of word sense disambiguation. Successfully differentiating these words not only represents an important step toward Chinese word sense disambiguation but also offers an instrumental facility for computer assisted Chinese learning. We aim at unsupervised clustering of a given set of such related Chinese words, where the quality of clustering results is to be judged based on the senses of the related words. In this preliminary study, we explored two approaches. We employed the bigram information of the related words that are available in ConceptNet 5 as the basis for clustering. We also relied on the general contexts of the related words to determine the clustering, where the general contexts were collected and computed based on news articles on the Internet. Algorithmic details and experimental results will be presented in the conference.