How to explain natural language processing (NLP) in plain English | The Enterprisers Project

Pose that question to Alexa – or Siri, Cortana, Google Assistant, or any other voice-activated digital assistant – and it will use natural language processing (NLP) to try to answer your question about, um, natural language processing.

That makes Alexa and its ilk a natural example of NLP in action: NLP is a core technology that enables virtual assistants to process your verbal queries and respond with some degree of accuracy.

But that doesn’t necessarily define NLP; it just points to a popular real-world application of NLP. Plus, the voice assistant example is actually too narrow: Natural language processing isn’t just about speech but also written text. Moreover, NLP is already ubiquitous, and your smartphone assistant is only one common example of its everyday use.

[ Check out our quick-scan primer on 10 key artificial intelligence terms for IT and business leaders: Cheat sheet: AI glossary. ]

“NLP is everywhere, and much farther-reaching than the more recently developed smart assistants,” says Keiland Cooper, director at ContinualAI and a neuroscience researcher at the University of California, Irvine. “Everything from search, email spam filtering, online translation, grammar- and spell-checking, and many more applications [use NLP]. Any machine learning that is done involving natural language will involve some form of NLP.”

Consider an email application that suggests automatic replies based on the content of a sender’s message, or that offers auto-complete suggestions for your own message in progress. A machine is effectively “reading” your email in order to make these recommendations, but it doesn’t know how to do so on its own. NLP is how a machine derives meaning from a language it does not natively understand – “natural,” or human, languages such as English or Spanish – and takes some subsequent action accordingly.

“Natural language is just the language humans use amongst themselves, as opposed to programming languages, which allow humans to tell machines what to do,” says Chris Nicholson, CEO of Skymind. “English is a natural language; Java is a programming language.”

Programming languages are written specifically for machines to understand. Our human languages are not; NLP enables clearer human-to-machine communication, without the need for the human to “speak” Java, Python, or any other programming language.

“Natural language processing is a set of tools that allow machines to extract information from text or speech,” Nicholson explains.

NLP is widely considered a subset of machine learning. It goes quite far back in the history of computing. NLP and machine learning both fall under the larger umbrella category of artificial intelligence.

“Natural language processing is simply the discipline in computer science as well as other fields, such as linguistics, that is concerned with the ability of computers to understand our language,” Cooper says. As such, it has a storied place in computer science, one that predates the current rage around artificial intelligence.

“To Alan Turing, who is considered to be the father of computer science, the bar for an artificially intelligent machine was one that could converse with a person so well that they wouldn’t be able to distinguish that they were talking to a computer,” Cooper says. “This is known as the Turing Test. So indeed, NLP is a very important part of computing.”

With this as a backdrop, let’s round out our understanding with some other clear-cut definitions that can bolster your ability to explain NLP and its importance to wide audiences inside and outside of your organization.

“NLP, or natural language processing, is a subfield of computer science that uses computer-based methods to analyze language in text and speech. It is used for practical purposes that help us with everyday activities, such as texting, e-mail, and communicating across languages.” –Jill Burstein, director of natural language processing research at Educational Testing Service

“NLP is an area of machine learning which deals with natural – human – languages. This is a broad field, dealing with problems ranging from speech recognition and transcription to text, to translation between different languages, to extracting entities such as people and locations from text, to providing natural language answers to natural language questions. In short, NLP gives machines the ability to read and understand human language – not to the extent humans can, but well enough to enable machines to perform simple tasks.” –Pavel Dmitriev, vice president, data science at Outreach

“NLP is a technology built to help computers process and analyze our language, both spoken and written. Essentially, engineers build NLP models to teach computers how to understand us and even replicate the way we communicate. This technology is used in a multitude of ways already, and there are countless future uses we’ve yet to see. The most widely used example of this would be the smart assistant we use on our phones. When we say, ‘Ok Google…,’ Google cloud first transcribes the audio to text, then uses NLP to understand what we’ve just said so that it can respond in the most effective way.” –Etienne Manderscheid, VP AI – machine learning at Dialpad

“NLP is the discipline of software engineering dealing with human language. ‘Human language’ means spoken or written content produced by and/or for a human, as opposed to computer languages and formats, like JavaScript, Python, XML, etc., which computers can more easily process. ‘Dealing with’ human language means things like understanding commands, extracting information, summarizing, or rating the likelihood that text is offensive.” –Sam Havens, director of data science at Qordoba.

But how does it actually work? Let’s dig into some examples you can use:

The Enterprisers Project is an online publication and community helping CIOs and IT leaders solve problems.

The opinions expressed on this website are those of each author, not of the author’s employer or of Red Hat. The Enterprisers Project aspires to publish all content under a Creative Commons license but may not be able to do so in all cases. You are responsible for ensuring that you have the necessary permission to reuse any work on this site. Red Hat and the Red Hat logo are trademarks of Red Hat, Inc., registered in the United States and other countries.