A Preferential Constraint Satisfaction Technique for Natural Language Analysis

In this paper, we present a new technique for the semantic analysis of sentences, including an ambiguity-packing method that generates a packed representation of individual syntactic and semantic structures. This representation is based on a dependency structure with constraints that must be satised in the syntax-semantics mapping phase. Complete syntax-semantics mapping is not performed until all ambiguities have been resolved, thus avoiding the combinatorial explosions that sometimes occur when unpacking locally packed ambiguities. A constraint satisfaction technique makes it possible to resolve ambiguities e ciently without unpacking. Disambiguation is the process of applying syntactic and semantic constraints to the possible candidate solutions (such as modi ees, cases, and word-senses) and removing unsatisfactory candidates. Since several candidates often remain after applying constraints, another kind of knowledge to enable selection of the most plausible candidate solution is required. We call this new knowledge a preference. Both constraints and preferences must be applied to coordination for disambiguation. Either of them alone is insu cient for the purpose, and the interactions between them are important. We also present an algorithm for controlling the interaction between the constraints and the preferences in the disambiguation process. By allowing the preferences to control the application of the constraints, ambiguities can be e ciently resolved, thus avoiding combinatorial explosions.