Abstract: A method of categorizing natural language text using a processor configured to execute instructions stored on a memory to perform the steps. The method includes selecting candidate keywords from a list of potential keywords based on the natural language text, the candidate keywords having a probability of success being greater than a threshold value. The method also includes generating, using a classification machine learning model (MLM), a list of candidate categories based on the potential keywords. The method also includes generating, using a similarity comparison MLM, a similarity score based on the candidate categories and a set of pre-determined categories. The method also includes assigning a selected category based on the similarity score to the natural language text.