Hownet and the computation of meaning

Abstract

It is widely acknowledged that natural language processing, as an indispensable means for information technology, requires the strong support of world knowledge as well as linguistic knowledge. This book is a theoretical exploration into the extra-linguistic knowledge needed for natural language processing and a panoramic description of HowNet as a case study. Readers will appreciate the uniqueness of the discussion on the definitions of the top-level classes HowNet specifies, such as things, parts, attributes, time, space, events and attribute-values, and the relations among them, and also the depth of the authors’ philosophy behind HowNet. The book presents the attraction of HowNet’s computability of meanings and describes how a software of the computation of meaning can collect so many relevant words and expressions and give a similiarity value between any two words or expressions.