Software requirements are often specified in natural language (NL). However, requirements specified in NL can often be ambiguous, incomplete, and inconsistent. Moreover, the interpretation and understanding of anything described in NL has the potential of being influenced by geographical, psychological and sociological factors. It is the job of requirements analysts to detect and fix any potential ambiguities, inconsistencies, and incompleteness in the requirements specifications documents. We are going to use Natural language processing techniques to extract quantitative data from the unstructured requirements and these are given to Generative adversarial Networks to generate the UML diagram
Selectus2/UMLGenNLP
Software requirements are often specified in natural language (NL). However, requirements specified in NL can often be ambiguous, incomplete, and inconsistent. Moreover, the interpretation and understanding of anything described in NL has the potential of being influenced by geographical, psychological and sociological factors. It is the job of requirements analysts to detect and fix any potential ambiguities, inconsistencies, and incompleteness in the requirements specifications documents. We are going to use Natural language processing techniques to extract quantitative data from the unstructured requirements and these are given to Generative adversarial Networks to generate the UML diagram
Python