In natural language processing applications, a corpus $($plural: corpora$)$ is a dataset involving text data $($e$.$g$.,$ sentences, tweets, documents$/$articles$,$ etc.$).$ A common subtask is modeling or representing word sequences based on that data $-$ essentially, keeping track of what words can follow what other words. This can be used in tasks like translation, sentiment analysis, part of speech tagging $($often a precursor to other tasks$),$ topic modeling $($or determining what an article$/$document$/$sentence is about$),$ speech recognition, authorship identification, etc. Here, we$$re going to use it for word prediction and text generation: if we know what word was just used, we can predict what word should come next based on wh