Shu-Ling Huang

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.

Knowledge Representation and Sense Disambiguation for Interrogatives in E-HowNet

In order to train machines to ‘understand’ natural language, we propose a meaning representation mechanism called E-HowNet to encode lexical senses. In this paper, we take interrogatives as examples to demonstrate the mechanisms of semantic representation and composition of interrogative constructions under the framework of E-HowNet. We classify the interrogative words into five classes according to their query types, and represent each type of interrogatives with fine-grained features and operators. The process of semantic composition and the difficulties of representation, such as word sense disambiguation, are addressed. Finally, machine understanding is tested by showing how machines derive the same deep semantic structure for synonymous sentences with different surface structures.