Document processing and text mining for requirement classification

The team of Grenoble INP developed this nugget, which is about document processing and text mining for requirement classification. The intended learning outcomes of this nugget are: identify the specificity of text data and method objectives, limitation, parameters, chose a suitable machine learning method/algorithm for problem solution and present a suitable solution based on data.

The nugget makes use of an industrial case to teach how to apply natural language processing (NLP) pipeline to extract requirements, and to apply machine learning techniques.