Preprocessing textual data
Language plays a very important role in our daily life. For us, reading a written text is very natural, but what about computers? Can they read it? Can we make our deep learning models generate new text based on the old pattern? For example, if I say, "Yesterday, I had ____ at Starbucks," most of us will be able to guess that the blank space is coffee, but can our deep learning models do it? The answer is yes; we can train our deep learning models to guess the next word (or character). However, deep learning models run on computers, and computers understand only binary, only 0s and 1s. Hence, we need a way to process out textual data so that it can be converted in to a form that is easy for the computer to handle. ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access