Semantic representation and composition for spatial concepts in Extended-HowNet

We distinguish two different types of spatial concepts, places and locations in Extended-HowNet by illustrating the representation of place nouns, place adverbs, and place prepositions. For a lexical knowledge representation system, it is necessary to encode both relational senses and content senses for each word. We add new features to the HowNet definitions for function words to represent concepts more precisely such that semantic composition process can be carried out while composing words into a phrase and phrases into a sentence. The new features include fine-grain semantic roles and their taxonomy. New event roles and directional functions are employed to define spatial concepts.