NELL’s subcategories from a question answering environment

With advances in machine learning, natural language processing, processing speed, and amount of data storage, conversational agents are being used in applications that were not possible to perform within a few years. NELL, a machine learning agent who learns to read the web, today has a considerably large ontology and while it can be used for multiple fact queries, it is also possible to expand it further and specialize its knowledge. One of the first steps to succeed is to refine existing knowledge in NELL’s knowledge base so that future communication between it and humans is as natural as possible. This work describes the results of an experiment where we investigate which machine learning algorithm performs best in the task of classifying candidate words to subcategories in the NELL knowledge base.