A measure of semantic complexity for natural language systems
Shannon Pollard, Alan W. Biermann · 2000
This paper will describe a way to organize the salient objects, their attributes, and relationships between the objects in a given domain. This organization allows us to assign an information value to each collection, and to the domain as a whole, which corresponds to the number of things to "talk about" in the domain. This number gives a measure of semantic complexity; that is, it will correspond to the number of objects, attributes, and relationships in the domain, but not to the level of syntactic diversity allowed when conveying these meanings.Defining a measure of semantic complexity for a dialog system domain will give an insight towards making a complexity measurement standard. With such a standard, natural language programmers can measure the feasibility of making a natural language interface, compare different language processors' ability to handle more and more complex domains, and quantify the abilities of the current state of the art in natural language processors.