Based on distributional data from BNC (predicate-object co-occurrence pairs), for an
input noun, the program retrieves 30 most similar ones. It also describes the
number of non-zero features for the target noun as well as its frequency rank in
* applied to non-normalized vectors. ** α = 0.001
*** D. Lin, 1998. Automatic Retrieval and Clustering of Similar Words. COLING-ACL98, Montreal, Canada, August, 1998.