Natural language processing for documentation analysis

In this WP we will apply technologies developed in the field of natural language processing to extract, organize and process information written in textual form that is useful for requirements acquisition.

We will take into account various kinds of documents, including those concerning the organization, documents on previous systems and transcripts of interviews with the stakeholders. The documents will be processed with tools for the morpho-syntactic analysis; their relevant terminology will be identified by the integration of statistical techniques with superficial text analysis. The extracted information will be organized by use of clustering and conceptual-indexing techniques. The expected outcome will be a structured lexicon, with references to the textual context related to it. This lexicon will constitute the base for an interactive support tool to be used in the requirements acquisition phase.


ResearchWP1 - Methodology and processWP2 - Specification and analysisWP3 - Verification and ValidationWP4 - Automated planningWP5 - Natural languageWP6 - Analysis and testingWP7 - ToolWP8 - Case study