Acquiring lexical knowledge using raw corpora and unsupervised clustering method

In this paper, we propose a computational model for automatic acquisition of lexical knowledge based on the principles of human language information processing. The proposed model assumes a hybrid model for the human lexical representation including full-list and decomposition forms. The proposed method automatically acquires lexical entries and its grammatical knowledge by unsupervised learning techniques. For the purposes of evaluating performance of the proposed method, a large-scale corpus of over 10 million lexical was used, the lexical knowledge acquisition process was tested, and the results were analyzed.