Distributedness and Non-Linearity of LOLITA's Semantic Network

摘要

This paper describes SemNet the internal Knowledge Representation for LOLITA. LOLITA is a large scale Natural Language Engineering (NLE) system. As such the internal representation must be richly expressive, natural (with respect to Natural Language), and efficient. In network representations knowledge is gleaned by traversing the graph. The paper introduces two properties, (distributedness and non-linearity) of networks which directly relate to the efficiency by which knowledge is obtained. SemNet is shown to have the specified properties thus distinguishing it (in terms of efficiency) as a suitable representation for large scale NLE.