Using Language and Context in the Analysis of Text

We describe a theory of natural language understanding within which we identify two separate components, a language centered one and a context centered one. xn5 rdrme* 1 component uses a knowledge Dase consisting of pairings of phrases with the concepts associated with them to determine the meaning of utterances. The latter component clarifies the meaning found by the first one and makes it more specific by attempting to reconcile it with the context of the utterance. We have constructed a program called PHRAN (PHRasal ANalyzer) which performs the task of the language centered component. At the root of this approach is the realization that previous attempts to process natural language in separate stages — first finding a syntactic p arse and then using semantic information to etermine the meaning of an utterance — were in error. Much research has been done in recent years demonstrating that semantic information is and should be used continually when processing text, and that it is wrong to assume that a separate syntactic parsing stage exists. But in arguing against the syntax-semantics distinction in processing, these natural language researchers have denied the existence of any discernible levels, or stages, in the process of understanding language and have argued that it is totally uniform. We claim that in fact there are two distinct levels of processing in the language understanding process: We will describe our model briefly here, and will then go over the separate components in more detail. A system called PHRAN (PHRasal ANalyzer) based on our view of the language centered component has been implemented, and will be extensively described in most of the paper. An outline of some of the ideas behind context centered processing will be given in section 5. 1.1 Brief Outline According to our model, in understanding a text the language centered component reads the text, recognizes the words and phrasal patterns in it, and produces conceptual fragments representing the meaning of the patterns plus other contextual information it may determine from its knowledge of the language. These fragments are accumulated in a buffer which is considered the context of the utterance. The context centered component looka at the conceptual fragments as they are introduced to this buffer and uses some world knowledge to introduce to it yet other related conceptualizations. It matches the appropriate fragments to slots that were left empty by the language centered process, and it clarifies …