TIL the difference between supervised learning and unsupervised learning. It’s about time. I mean, I work for in an NLP/machine learning team at a startup that uses machine learning to make things. I ought to know it by now. I guess it helped that I heard these terms thrown about left and right. We all learn at our own pace.
I came across the Wikipedia page for statistical classification, and this short paragraph just jumped out to me:
In the terminology of machine learning, classification is considered an instance of supervised learning, i.e. learning where a training set of correctly identified observations is available. The corresponding unsupervised procedure is known as clustering, and involves grouping data into categories based on some measure of inherent similarity or distance.
Now I understood why we had used terms like ‘clustering’ at work. When we grouped together sentences, it was an unsupervised procedure – clustering – based on cosine similarity. If we had used some sort of heuristics to label a subset of the data, then train the rest of the data, that would have been supervised learning.