A form of artificial intelligence known as natural language processing (NLP) makes modern travel a lot more modern.
Anyone who’s booked a train ride in the US knows “Ask Julie,” the virtual travel assistant Amtrak introduced in 2001. Her cheerful demeanor has made Julie into a success story in customer service automation delivered with a human touch. Amtrak earns 30 percent more revenue on 25 percent more bookings than it could without Julie’s NLP technology handling the bulk of the call volume.
Yet effective use of NLP, enabled by two other key technologies called natural language understanding (NLU) and natural language generation (NLG) now deliver much more business impact beyond just improved customer service. “These technologies are the engines behind game-changing improvements in how marketing messages are created, personalized and scaled for enterprise companies,” said Frank Chen, NLP Scientist at Persado. “The benefit of using NLG-generated marketing messages and powerful statistical methods such as the ones Persado uses is that brands can deliver higher performing messages generated by NLG, but also understand how each component performs and which contributes the most to the outcome.”
Many marketing leaders and CMOs need to better understand how to effectively scale their personalization and marketing campaigns in ways that deliver better customer experiences and ultimately, business results.
That’s where NLP and it’s artificial intelligence (AI) cousins NLU and NLG come in.
Computer scientists tend to view NLP as an umbrella field of AI that includes NLU and NLG. To understand how they work and what they bring to marketing, however, it’s helpful to look at each separately.
By changing positions, words and phrases, Persado teams using NLG can easily produce an enormous number of winning creative combinations for client messaging.
– Frank Chen, Persado NLP Scientist
NLP technology converts human language into structured data that a computer can interpret. Think of NLP as allowing a computer to read text written in normal human language.
Before NLP, all the queries that came into an organization, from emails to call center requests, had to be read or listened to by a human agent because only humans could see that the words were words. Just as challenging was the fact that the content of all those interactions couldn’t be easily captured and analyzed to drive improvements.
NLP changes that.
By providing a way to capture language and convert it into interpretable data, NLP vastly improves the speed with which companies can take in information or requests as humans usually deliver them: in natural speech.
NLU is the technology that interprets human language to identify what the customer needs. Slang, mispronunciation, regional accents, and the daily challenges of syntax make it difficult for machines to interpret what a person says, let alone what they mean.
NLU solves those challenges.
When integrated with the Interactive Voice Response (IVR) software used in call centers, or with personal assistants like Siri or Alexa, NLU technology allows customers to speak as they normally do. The system then does the work to interpret their words and route them to the right agent or turn on the requested function.
Learn more: Discover Natural Language Understanding
NLG technology produces verbal or written text that sound like a human wrote it. When used in conjunction with NLP and NLU, NLG generates natural, context appropriate, and helpful responses to a customer question or request.
NLG makes personalized marketing at scale possible.
In the case of Julie, she listens as a customer explains what they need, interprets the request, finds the answer, and then delivers her response back in conversational language. Need to book a ticket to Boston? “Sure, I can take care of that” is NLG in action.
Customer service applications like Ask Julie were among the earliest and continue to be the most common applications of NLP, NLU and NLG technology. In business, these solutions allow organizations to automate customer interactions through call centers, website chatbots, and email, and still maintain a human touch.
Yet these technologies are increasingly moving beyond efficiency applications into areas of the business where they can create significant value across the entire enterprise. Financial institutions, for example, use NLP and NLG technology to automate production of financial reports that use the same sources of data in the same way, ensuring consistency. Retailers are experimenting with using NLG to write thousands of on-brand product descriptions. The Gartner Hype Cycle for Artificial Intelligence 2019 shows NLP sliding into the “trough of disillusionment,” which means it’s well on its way toward full productivity.
Marketing leaders are actively investing in NLG technology. Without NLG marketers wouldn’t be able to personalize content or creative messages at scale and at the fast pace that business requires today. The potential value for multichannel marketing is clear.
“Making NLG successful in marketing is not just about building a vocabulary for marketing,” says Persado’s Chen. “It’s about grouping words and phrases into a hierarchical database of categories and phrases related to the emotions or ideas that work best with a brand’s audience. That delivers thousands of ways to express a given emotion or sentiment. To communicate urgency, for example, the system could generate the phrase ‘Open now to claim,’ ’Expiring soon’, or ’You’re running out of time.’ By changing positions, words and phrases, Persado teams using NLG can easily produce an enormous number of winning creative combinations for client messaging.”
In this way, NLG can produce enough content for each channel at scale, while preserving the human touch audiences expect and the consistent brand voice marketers require. From customer service to customer engagement, NLP, NLU and NLG technologies are allowing brands to communicate with more customers in ways that marry technical automation with a human touch.
Just ask Julie.