Resolving Quasi Logical Forms
Hiyan Alshawi · 1990
This paper is concerned with the relationship between the linguistic analysis of sentences and their interpretation in context. Our model is described as implemented in the Core Language Engine (CLE), a domain-independent system for translating natural language sentences into logical form representations. One of the characteristics of this system is that it embodies an extreme form of a staged natural language processing architecture whereby modular processing components have the function of mapping between different levels of sentence representation. Representations at the level of quasi logical form (QLF) are the result of applying declarative rules for morphological, syntactic, and semantic analysis. These QLF representations have subexpressions corresponding to unresolved referring constructions. The QLF level can be regarded as the natural level of sentence representation resulting from compositional semantic analysis independently of the influence of context: Serttertce-LINGUISTIC ANALYSIS --- QLFs-QLF RESOLUTION IN CONTEXT---LF