From the course: Introduction to Artificial Intelligence

Natural language processing

From the course: Introduction to Artificial Intelligence

Natural language processing

“

- As humans, we're always trying to do a better job of communicating, so it's no surprise that we want to communicate with our machines. In many ways, machine-to-machine communication is much more accurate than human communication. Computer networking transmits exact copies of information at lightning speeds. Humans, on the other hand, are always struggling to reach greater understanding. If you can deliver 10% of what you're intending, then you're a master communicator. That means that the machines we rely on must do a better job of communicating in our world. To achieve this, AI programs do something called natural language processing. This is when you interact with the machine using your own natural language. You can talk with the machine in the same way you talk with other humans. We're all familiar with communicating with a search engine like Google. There's a little box and then you type in questions. You can type something like recipe for Belgian waffles. Then the search engine will match your phrase to popular results. Now with some smart devices, instead of typing, you could say this in natural language. You could use natural language like could you give me a good recipe for those big, fluffy waffles? It's very common for humans to describe things by their attributes. In this case, good, big and fluffy. To understand the request, the system uses natural language processing. The machine needs to understand that good is relative, so in this case the person probably is looking for top recipes. The machine also must figure out what's a big fluffy waffle? Modern natural language processing uses machine learning and artificial neural networks. It looks through millions of conversations to identify patterns. So if it sees conversations with the word big, fluffy, and Belgian waffles, then it knows that there's a pattern between these words. That's why many companies like Google, Microsoft, and Apple offer free email, voicemail, or text. It's a way to have their artificial neural networks look through conversations to better identify patterns. But natural language processing isn't just about understanding the words, it's also understanding the context and meaning. A few years ago, one of the top Google searches was what is love? Humans have written on love from the beginning of language, so there's sure to be plenty of data on the topic. At the time, Google would give you a long list of results. Some of them were about biological pairing rituals and the importance of feeling connected. This was the kind of response you'd expect from a network that's just matching keywords in the database. There was nothing natural or human about it. It was just matching keywords in the database. Natural language processing gives the machine the ability to understand the larger world. If you're typing in what is love, then you're probably more interested in romantic notions of love, perhaps even some poetry or insights into what it's like to be in love. Now with natural language processing, the Google response is much more thoughtful. You can see lists of poems in the history of romance, but natural language processing is more than just love and waffles. Communication is at the very core of what it means to be human. That's how we organize, empathize, and understand each other. Humans would never accept a machine as intelligent if it wasn't capable of natural communication.

Contents