Reversible NLP by Deriving the Grammars From the Knowledge Base

REVERSIBLE NLP BY DERIVING THE GRAMMARS FROM THE KNOWLEDGE BASE David D. McDonald Content Technologies, Inc. 14 Brantwood Road, Arlington, MA 02174 (617) 646-4124, MCDONALD@BRANDEIS.EDU ABSTRACT We present a new architecture for reversible NLP. Separate parsing and generation grammars are constructed from the underlying application's semantic model and knowledge base. By having two grammars we are free to use process-specific representations and control techniques, thereby permitting highly efficient processing. The single semantic source ensures the parsimony of development and matched competence that make reversible NLP attractive. INTRODUCTION Most natural language processing systems are initially built in a single direction only; most are parsers (understanding systems), a few are generators. These systems are often then embedded in full, bi- directional interfaces, whereupon a new, almost non- technical kind of problem arises if differences in the two uni-directional subsystems are not controlled. The full system may not understand the same wording or syntactic constructions that it can generate; or generation and parsing development teams may both have to work on extensions and modifications to their grammars, with the likely result that still further differences will be introduced. These practical problems bolster an intuition that many have that knowledge of parsing and generation is the same knowledge in a person's mind, or at least that the two faculties draw on a single representation of their language even if it is engaged in different ways. This has led to the goal of reversible NLP systems. The common approach has been to take the computational artifact constructed by one of the single-direction projects, typically its grammar, and to aSapt it for use in the other direction. At ISI, for example, their massive systemic grammar for generation, NIGEL, (Mann & Matthiessen 1985) has since been adapted for use as a parser (Casper 1989). With the conceptual basis of the transformation in place, the development of further extensions and modifications is done on the generation grammar, and then that grammar is re- transformed to yield the new parsing grammar. The other well-known approach to reversible NLP is of course to use the very same computational artifact in both processing dkections. Thus far this artifact has invariably been a grammar, typically some kind of specification of the text-stream -- logical form relation that can be used as a transducer or can supply the data for it. Parsers and generators draw on their grammars as their predominant knowledge source. The grammar thus becomes a bottleneck for the processing if it is not designed with efficiency of processing in mind. When virtually the same computational representation of the grammar is used in both processes and it is given an active role, e.g. when the grammar is couched in a unification formalism, this bottleneck can be substantial since the "common denominator" processing architecture that must be employed in order for the grammar to be literally usable by both processes will be markedly less efficient than architectures that work from single-direction representations of the grammar. By their nature as information processing systems, …

Content truncated to 500 words