Originally published on
Artificial intelligence (AI) is changing the way we look at the world. AI “robots” are everywhere. From our phones to devices like Amazon’s Alexa, we live in a world surrounded by machine learning.
Google, Netflix, data companies, video games and more all use AI to comb through large amounts of data. The end result is insights and analysis that would otherwise either be impossible or take far too long.
It’s no surprise then that businesses of all sizes are taking note of large companies’ success with AI and jumping on board. Not all AI is created equal in the business world, though. Some forms of artificial intelligence are more useful than others.
Today, I’m touching on something called natural language processing (NLP). It’s a form of artificial intelligence that focuses on analyzing the human language to draw insights, create advertisements, help you text (yes, really) and more.
But why natural language processing?
NLP is an emerging technology that drives many forms of AI you’re used to seeing. The reason I’ve chosen to focus on this technology instead of something like, say, AI for math-based analysis, is the increasingly large application for NLP.
Think about it this way. Every day, humans say thousands of words that other humans interpret to do countless things. At its core, it’s simple communication, but we all know words run much deeper than that. There’s a context that we derive from everything someone says. Whether they imply something with their body language or in how often they mention something. While NLP doesn’t focus on voice inflection, it does draw on contextual patterns.
This is where it gains its value. Let’s use an example to show just how powerful NLP is when used in a practical situation. When you’re typing on an iPhone, like many of us do every day, you’ll see word suggestions based on what you type and what you’re currently typing. That’s natural language processing in action.
It’s such a little thing that most of us take for granted, and have been taking for granted for years, but that’s why NLP becomes so important. Now let’s translate that to the business world.
Some company is trying to decide how best to advertise to their users. They can use Google to find common search terms that their users type when searching for their product.
NLP then allows for a quick compilation of the data into terms obviously related to their brand and those that they might not expect. Capitalizing on the uncommon terms could give the company the ability to advertise in new ways.
So how does NLP work?
As mentioned above, natural language processing is a form of artificial intelligence that analyzes the human language. It takes many forms, but at its core, the technology helps machine understand, and even communicate with, human speech.
But understanding NLP isn’t the easiest thing. It’s a very advanced form of AI that’s only recently become viable. That means that not only are we still learning about NLP but also that it’s difficult to grasp.
I’ve decided to break down NLP in layman’s term. I might not touch on every technical definition, but what follows is the easiest way to understand how natural language processing works.
The first step in NLP depends on the application of the system. Voice-based systems like Alexa or Google Assistant need to translate your words into text. That’s done (usually) using the Hidden Markov Models system (HMM).
The HMM uses math models to determine what you’ve said and translate that into text usable by the NLP system. Put in the simplest way, the HMM listens to 10- to 20-millisecond clips of your speech and looks for phonemes (the smallest unit of speech) to compare with pre-recorded speech.
Next is the actual understanding of the language and context. Each NLP system uses slightly different techniques, but on the whole, they’re fairly similar. The systems try to break each word down into its part of speech (noun, verb, etc.).
This happens through a series of coded grammar rules that rely on algorithms that incorporate statistical machine learning to help determine the context of what you said.
If we’re not talking about speech-to-text NLP, the system just skips the first step and moves directly into analyzing the words using the algorithms and grammar rules.
The end result is the ability to categorize what is said in many different ways. Depending on the underlying focus of the NLP software, the results get used in different ways.
For instance, an SEO application could use the decoded text to pull keywords associated with a certain product.
When explaining NLP, it’s also important to break down semantic analysis. It’s closely related to NLP and one could even argue that semantic analysis helps form the backbone of natural language processing.
Semantic analysis is how NLP AI interprets human sentences logically. When the HMM method breaks sentences down into their basic structure, semantic analysis helps the process add content.
For instance, if an NLP program looks at the word “dummy” it needs context to determine if the text refers to calling someone a “dummy” or if it’s referring to something like a car crash “dummy.”
If the HMM method breaks down text and NLP allows for human-to-computer communication, then semantic analysis allows everything to make sense contextually.
Without semantic analysts, we wouldn’t have nearly the level of AI that we enjoy. As the process develops further, we can only expect NLP to benefit.
NLP and more
As NLP develops we can expect to see even better human to AI interaction. Devices like Google’s Assistant and Amazon’s Alexa, which are now making their way into our homes and even cars, are showing that AI is here to stay.
The next few years should see AI technology increase even more, with the global AI market expected to push $60 billion by 2025 (registration required). Needless to say, you should keep an eye on AI.