Natural language generation (NLG) is taking the world by storm as a wave of billion-dollar language startups are upending how humans create content and interact with machines.
But exactly is NLG? And how is it different from other AI language technologies?
At Marketing AI Institute, we've spent years studying AI technologies and their impact on marketing—including NLG. We've distilled our expertise into this post, which contains everything you need to know about this transformative AI technology.
What Is Natural Language Generation?
Natural language generation (NLG) is the process of transforming data into natural language using artificial intelligence.
NLG software does this by using artificial intelligence models powered by machine learning and deep learning to turn numbers into natural language text or speech that humans can understand.
Chatbots, voice assistants, and AI blog writers (to name a few) all use natural language generation. NLG systems can turn numbers into narratives based on pre-set templates. They can predict which words need to be generated next (in, say, an email you're actively typing). Or, the most sophisticated systems can formulate entire summaries, articles, or responses.
What Is the Difference Between NLG and Natural Language Processing (NLP)?
NLG is the process of translating data into text or speech using AI. Natural language processing (NLP) is what gives NLG that data.
Natural language processing is the process of accurately translating what you say into machine-readable data, so that NLG can use that data to generate a response.
After all, the machine has to "understand" the prompt or conversation in order to craft a response. Put another way: NLP reads (or hears), while NLG writes (or speaks).
What Is the Difference Between NLG and Natural Language Understanding (NLU)?
NLP translates what you say into data. An NLG system uses that data to generate language. But what if the machine's answer makes no sense? That's where natural language understanding (NLU) comes in.
Natural language understanding is AI that uses computational models to interpret the meaning behind human language. It analyzes the data produced by NLP to understand the meaning of your words and the relationships between concepts.
NLG generates language that sounds human. NLU makes sure that human-sounding language actually means something. If the NLU does its job, you get a response from a chatbot or voice assistant that makes perfect sense.
Applications of Natural Language Generation
NLG technology has countless commercial applications, and you almost certainly experience NLG daily—whether you realize it or not.
Here are just a handful of examples of advanced NLG applications:
- Chatbots that automatically answer questions on websites.
- Voice assistants like Alexa or Siri that respond to commands.
- Machine translation tools that translate one language into another.
- Conversational AI assistants that use advanced NLG and NLU to carry on two-way conversations.
- Analytics platforms can use NLG to explain insights from your data in easy-to-understand language.
- AI blog writers for content creation can use a language model to automatically write anything from a sentence to an entire article.
- Sentiment analysis platforms use NLU to understand which language resonates with customers, then employ NLG to create messages they're likely to respond to.
- AI-powered transcription tools use speech recognition to understand audio, then NLG to turn it into text.
- Narrative generation tools use structured data (often in the form of a spreadsheet) to automatically generate a text narrative.
These are just a few of the broad ways NLG is used in business and consumer life. Let's now take a look at some specific companies that develop NLG for these use cases.
Natural Language Generation Tools
There are thousands of NLG tools that use AI and machine learning to write and speak in commercial applications.
Here at Marketing AI Institute, we track thousands of AI vendors. So, we have a good sense of top tools that do NLG. Here are some to explore:
Arria uses NLG to extract and summarize data into readable narratives.
Automated Insights uses NLG to help organizations create earnings reports at scale, sports articles (box scores, results, etc.), and data-driven narratives.
Clickvoyant uses NLG to dramatically reduce the time it takes to extract insights from analytics and create presentations based on those insights.
Drift uses conversational NLG to remove friction from the buying process with chat, email, video, and automation products.
Exceed.ai uses AI to engage with every sales lead that enters your pipeline, using human-like, two-way conversations by email and chat.
Hyperwrite is an NLG tool that automatically writes sentences and paragraphs based on prompts provided by a human.
MarketMuse is an AI-driven assistant for building content strategies and creating content. It uses NLG to create summarized briefs telling you how to write posts for maximum impact and will even automatically generate text for you.
Narrative Science uses NLG to take structured data (spreadsheets) and turn them into human-sounding narratives.
Pencil uses NLG to automatically generate better-performing Facebook ads.
Persado uses NLG to generate marketing copy and creative to create the best possible messaging for your individual prospects across channels.
Phrasee uses NLG to automatically write email subject lines better than humans, resulting in higher open rates.
Yseop uses NLG to automatically generate narratives from data across financial and medical reporting.
Now that you have some ideas of NLG vendors out there, why not get started using the technology yourself?
How to Get Started with Natural Language Generation
Getting started with NLG in business and marketing requires some thought and planning.
Here are some initial steps you can take to accelerate NLG adoption in your business.
1. Determine if you have a use case for basic NLG.
Look first to the stories you're already manually telling with numbers. Think about "stories" as any narratives that make sense of data. This might include external-facing or internal-facing reports, summaries, fact sheets, etc.
Do you produce these types of stories regularly? Are any of these narratives in a consistent, repeatable formats (i.e. you're reporting on or telling a story about the same types of numbers each week or month)?
These might be candidates for natural language generation.
PR 20/20 , the marketing agency behind the Marketing Artificial Intelligence Institute, has used NLG to cut down analysis and production time of Google Analytics reports by 80%. This isn't an advanced NLG use case that leverages something as robust as GPT-3, but it is a valuable one.
It just goes to show that low-hanging fruit may create value faster for your organization, while teaching you the basics of natural language generation.
2. Look at how your data is structured.
Even with a use case, natural language generation needs structured data to work.
Are your datasets organized in ordered columns and rows? The current NLG solution we use requires a CSV upload, so data needs to be clean and relatively consistent to get value out of this technology.
Or, you may need to invest time into cleaning up your data before uploading it to a system that uses natural language generation.
3. Be realistic about your ROI.
NLG solutions, even basic ones, typically require substantial time to set up. You also need to pay for a solution, and possibly related NLG services. You'll want to take a realistic look at the technology, what it can do for you, and how much you can scale using it.
Start by analyzing how long reports, articles or narratives currently take, then see how much time NLG can potentially shave off.
Finally, apply those time savings to all staff whom NLG would affect. An hour saved per week per employee may make financial sense for your organization.
GPT-3 and the Future of Natural Language Generation
The most impressive advances in NLG have only happened recently—and the field is moving at warp speed.
As far back as 1986, research was published on possible NLG use cases. Ten years later, researchers at the University of Aberdeen were publishing about how to use the technology for text and sentence planning. As late as 2006, obstacles to NLG adoption were still being defined and discussed among leaders in the field.
Yet 2019 turned out to be the real banner year for NLG. It was then that OpenAI, a non-profit AI research company, announced they built an AI model that essentially writes coherent paragraphs of text at scale. The model was called GPT-2 and it learned how to write this well by analyzing eight million web pages.
GPT-2 led to GPT-3, a model released just one year later than uses 100X more data than its predecessor—and is 10 times more powerful. GPT-3 is now one of the most popular NLG text generation models used today. It's increasingly used to generate text that is nearly indistinguishable from human-written sentences and paragraphs.
That means, soon enough, the next time you have a conversation online, you might not even realize you're talking with a machine.
As Chief Content Officer, Mike Kaput uses content marketing, marketing strategy, and marketing technology to grow and scale traffic, leads, and revenue for Marketing AI Institute. Mike is the co-author of Marketing Artificial Intelligence: AI, Marketing and the Future of Business (Matt Holt Books, 2022). See Mike's full bio.