Each tool uses a fixed codebase to process syntax, plus an optional semantic module (right side). The core memory manager (yellow) maintains a set of application-specific Topic Maps, which enable both new (green) modules:

TRANSCRIBER - analyzes text structures in high-speed memory

Our INTERPRETER is really a suite of support utilities for doing such things. Able to operate as a standalone package, it includes a search engine for semantic net models that can record an NLP transcription chart as saved memory models, use it to find similar ones and/or trigger rule-based reaction scripts that call independent processes.

Known as AGENCY, this graph-handling suite can be driven by imported DB tables or controlled English inputs as well as the situational case frame charts that typically emerge from our multi-stage NLP analysis. In any usage, the helpful ways in which it can react to semantic graphs of triples is its value proposition.

MODELER - manages topic models in a mid term memory

Either way, CONTEXT models the result under our ontology for Idealized English, which covers a discourse model for handling anaphora, plus a powerful set of open-source semantic constraint patterns that can formally associate or annotate topics to denote whatever WORDS expressions said about them.

SCANNER - finds needed lexical data in long term memory files

The THESAURUS option adds to each token broad-coverage (surface) semantic models for case frames of common verbs and prepositions, contextually ranked and filtered. To provide for specific vocabulary expected in your own application, it also helps you interactively build up extension lexicons from training texts.