Natural language processing (or NLP for short) refers to technology that allows computers to understand human language. NLP is what helps computers read, edit and summarise text – as well as enabling natural language generation (NLG), whereby computers generate their own “speech.” In other words, NLP is the technology that enables Siri to understand your requests, while NLG means Siri can respond in natural-sounding language.

Examples of NLP in action

Smart digital assistants like Alexa and Siri are among the best-known examples of NLP in action. Predictive text and email spam filters are earlier examples.

One of my favorite examples is the popular grammar tool Grammarly, which provides a spelling and grammar cheque for your Word documents, email, and social media posts. (You can download a Grammarly plug-in for Microsoft Office, get an extension for Chrome, and download a Grammarly keyboard for your mobile devices.) The AI-based system was trained using examples of correct and incorrect grammar, punctuation, and spelling, but it’s constantly evolving and learning. For example, when a user ignores a Grammarly suggestion, the system learns from that in order to deliver more relevant suggestions in the future.

Why NLP is such a key trend

NLP is a critical technology trend because so much of the world’s information is in the form of natural human language. Think of all the information out there in the form of emails, WhatsApp messages, Twitter updates, news articles, books, spoken conversations, and so on. NLP allows machines to unlock all this information and extract meaning from it.

Traditionally, extracting meaning from language was incredibly difficult for machines. Human language is messy, complicated, and unstructured, and a far cry from the highly structured data that machines are used to dealing with. AI has changed all that. Thanks to AI technologies such as machine learning, coupled with the rise of big data, computers are learning to process and extract meaning from text – and with impressive results.

4 ways businesses can make use of NLP technology

Let’s look at some of the main ways in which companies are adopting NLP technology and using it to improve business processes.

1. Speech recognition

We know from virtual assistants like Alexa that machines are getting better at decoding the human voice all the time. As a result, the way humans communicate with machines and query information is beginning to change – and this could have a dramatic impact on the future of data analysis. In a business context, decision-makers use a variety of data to inform their decisions. Traditionally, accessing this data meant using a dashboard or other analytics interface and sifting through the various metrics and reports available. But now, thanks to NLP, some data analytics tools have the ability to understand natural language queries. In other words, instead of sifting through the information to extract insights, users can simply speak or type their questions (such as, “Who are our best performers this week?”) and get a meaningful response. As an example of this, Sisense analytics engines integrate with Alexa.

2. Sentiment analysis

As well as understanding what people are saying, machines can now understand the emotional context behind those words. Known as sentiment analysis, this can be used to measure customer opinions, monitor a company’s reputation, and generally understand whether customers are happy with a product or service. Sentiment analysis is now well established, and there are many different tools out there that will mine what people are saying about your brand on social media in order to gauge their opinion. The technology can be extraordinarily perceptive. In one example, researchers at the Microsoft Research Labs in Washington were able to predict which women were at risk of postnatal depression just by analyzing their Twitter posts. What’s even more impressive is the research was based on what women were saying in the weeks before giving birth.

3. Automatic summarization

I’ve already alluded to how much information is wrapped up in human language, whether written or spoken. For some sectors – I’m thinking of the legal system as a prime example – the ability to easily extract key information from thousands of pages of documents could be a real game-changer. Tools such as MeaningCloud and ML Analyser can automatically summarise long documents into short, fluent, and accurate summaries. They can also be used to extract keywords.

4. Chatbots

Closely linked with speech recognition, chatbots are another useful business tool powered by NLP. Chatbots are everywhere these days – on the websites you browse, in messenger platforms, and in apps – and the technology is helping to streamline a range of business processes, including customer service, sales, and even HR. If you’voe interacted with a brand via messaging lately, chances are you were chatting with a bot. And although the technology is far from perfect, it’s definitely getting harder to tell whether we’re talking to a human or a computer.