DYNAMIC GENERATION OF ALTERNATIVE QUESTIONS

In one embodiment, a method includes storing machine learning classification models, retrieving metadata including a plurality of terms, each of the terms include a question side value and an answer side value, categorizing each of the terms into a particular type and identifying the answer side value of each of the plurality of terms, executing instructions to cluster the question side values and answer side values according to one or more criteria, receiving text input including a first term, retrieving the one or more clusters of question side values and answer side values corresponding to the text input of the first term, filtering and ranking the clusters of question side values and answer side values based on one or more attributes corresponding to the first term, determining a first cluster of question side values and answer side values are ranked above a predetermined threshold, displaying the alternative questions.