A knowledge-based methodology applied to linguistic engineering

A methodological approach to the design of structured knowledge models for natural language processing (NLP) applications that takes the inherent interdisciplinarity of this area into account and deals with the linguistic knowledge involved in these systems.

Abstract

A methodological approach to the design of structured knowledge models for natural language processing (NLP) applications is presented. It takes the inherent interdisciplinarity of this area into account and deals with the linguistic knowledge involved in these systems. The key features of the modeling methodology comprise the decomposition of linguistic knowledge sources in specialized sub-areas to tackle the complexity problem and a focus on cognitive architectures that allow for modularity, scalability and reusability. This methodology is operationalized through a tool that allows software development of real knowledge-based applications in a modular way. Text interpretation for conceptual database modeling is described using this methodology, extracting the relevant information for application purposes by using different linguistic cues and by following various analysis paths.