At the most basic level, computers communicate using binary code—zeros and ones. To get from bits and bytes to conversational English—or any other human language—requires complex technological development. It’s been a long time coming, but the area of artificial intelligence (AI) called natural language processing, or NLP, has finally advanced to the point where apps can stand in for human agents in a multitude of ways, many of which are cropping up in eLearning and performance support tools. This article describes a few ways L&D teams are already using NLP in eLearning, but it is far from a complete list.

What is NLP?

NLP technologies parse complex human language, using algorithms to identify parts of speech, analyze syntax, and figure out the function of each word in a phrase or sentence. They can then decipher the meaning of a comment or request and respond appropriately. NLP draws on other areas of AI, such as machine learning and deep learning, technologies that enable computers to “learn” to perform tasks that humans typically perform, including recognizing speech, learning speech patterns and variations, and formulating responses that mimic human conversation. These technologies make it possible for NLP-powered apps to work fluidly, rather than being limited to a predetermined set of responses. The ability of AI-powered technology to learn and build on experience and inputs has moved computers from the era of programmed inputs into what the Future Today Institute calls “cognitive” computing—an age where computers problem-solve and apply reasoning.

A person using an NLP-based technology might speak to the app or device, type, or input text in another way: When a learner asks Siri a question, instructs her smart speaker to play music, or dictates a text or email, she’s using NLP. Alternatively, a learner can type into an email or texting app, and an NLP-powered feature might suggest word completions. Email programs that suggest a response to an incoming message are also using NLP.

In many languages, words can have different meanings depending on the context in which they are used. This “structural ambiguity” presented enormous challenges in the development of NLP algorithms. Madly Ambiguous, an online game where players attempt to trip up the computer, shows—and explains—how one NLP algorithm deals with structural ambiguity by “learning” all possible meanings of a word, then analyzing the other words in a phrase to tease out the correct meaning for a specific context.

NLP in eLearning

With the technology integrated into many apps and tools, learners might not realize how frequently they are using natural language processing in eLearning.

For instance, any chatbot-based performance support tool relies on NLP—and chatbots are increasingly adept conversationalists. People don’t always know (or care) that they are interacting with a chatbot: Many students using chatbot-based virtual assistant at Georgia Tech didn’t even realize that “she” wasn’t human, according to Artificial Intelligence Across Industries: Where Does L&D Fit?, a Guild Research report by Jane Bozarth.

In the eLearning context, chatbots might:

  • Provide first-line customer service or technical support, responding to common, routine queries and escalating more complex problems to a human agent
  • Guide new employees through an onboarding process, alerting them to tasks they need to complete, reminding them of deadlines, and sending them information or links to forms
  • Coach learners between face-to-face or virtual classroom sessions, reviewing material covered or asking quiz questions
  • Check in with trainees, asking them to reflect on skills learned or observations
  • Provide spaced practice and drills to supplement or reinforce eLearning or face-to-face training
  • Offer performance support by answering questions, linking employees to information or documents, assisting with basic tasks, or stepping them through seldom-used processes

Voice-based virtual assistants are not restricted to chatbots on mobile devices. Smart devices, reportedly used by more than 50 million American adults, are already performing routine office tasks. In some companies, voice-activated assistants schedule conference calls and connect participants, for example.

NLP-powered apps can create text as well as interpret it. Within L&D, NLP can be used to:

  • Generate short content based on keywords, streamlining the content creation process
  • Extract keywords from existing content, categorizing content, facilitating searches, and helping identify relevant eLearning and deliver it to learners
  • Summarize long texts by identifying key themes or ideas, aiding in chunking of long content and targeting of content to learners
  • Determine whether a passage, such as a comment on an eLearning “smile sheet,” indicates a positive or negative sentiment, a useful way to gauge learners’ responses to eLearning
  • Identify patterns or themes across multiple texts to categorize, curate, and target content
  • Translate between languages, enabling cross-cultural conversation and document sharing among employees at global companies
  • Animate virtual trainers and make branching scenarios in eLearning more dynamic and engaging
  • Create voice-activated performance support tools that allow employees to get assistance in the workflow

Put NLP to work in eLearning

Consumers are accustomed to using virtual assistants on their smartphones, tablets, and smart speakers; they’ve been using auto-complete for years. As digital learners, those individuals expect to use the same technologies to do all of that and more. Using NLP in eLearning and performance support is a no-brainer. Learn more about NLP and other emerging technologies at The eLearning Guild’s DevLearn Conference & Expo, October 24 – 26, 2018, in Las Vegas.