What Is Natural Language Generation (NLG)?
Natural language generation (NLG) is the process of transforming data into natural language.
This is done through the use of statistical techniques which analyze large datasets and use them to generate natural-sounding sentences.
NLG can be used in a variety of fields, including journalism, marketing, financial reporting, and customer service.
NLG systems aim to generate text from structured knowledge or information such as databases and ontologies.
These systems generate natural language in a variety of formats.
They 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.
With the right data in the right format, a natural language generation system can automatically turn numbers in a spreadsheet into data-driven narratives or even use associations between words to create partially or fully machine-written text.
NLG has been a field of AI research for decades, but the most impressive, and useful, advances in the technology have only happened recently.
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 today you use NLG every day whether you know it or not.
A system like Gmail's Smart Compose now offers suggestions on what you should type next in an email. Then, it learns each time you pick one of its suggestions. It's using advanced NLG and NLP to read your emails while you write them, then predict what you are trying to say next-in real-time.
The Associated Press uses NLG to automatically create machine-written corporate earnings reports.
In the past, a human reporter reviewed earnings data when it was released, then wrote a report on it.
Today, the AP uses NLG to ingest that data, then produce a narrative in seconds, freeing up reporters to pursue higher-value tasks within the organization.
All the AP earnings reports follow the same exact format. So, once NLG is set up, their system can produce thousands of stories at scale.
Even weirder, in 2019 OpenAI, a non-profit AI research company, announced they built an AI model that essentially writes coherent paragraphs of text at scale.
The model is called GPT-2 and it learned how to write this well by analyzing eight million web pages. In 2020, OpenAI updated the model and released GPT-3.
In early experiments, GPT-3 has been used to produce everything from coherent blog posts to press releases to technical manuals, often with a high degree of accuracy.
To do that, GPT-3 uses 175 billion parameters in its language model, compared to GPT-2's 1.5 billion.
It's still early days for GPT-3, and the validity of the model hasn't been fully explored. But one thing should give marketers pause:
The speed of improvement in OpenAI's language models.
The first GPT model came out in 2018. GPT-2 was released with greatly expanded capabilities in 2019.
Just a year later, GPT-3 uses 100x as much data as its predecessor and is beginning to display incredible content creation capabilities, including turning text into code and evaluating investment memos.
This type of machine-powered language generation has serious implications for marketers.
With properly structured data, marketers can use NLG to automate some narratives that are based on data.
That might include analytics reports, data-driven sections of blog posts, product descriptions with standardized formats and lots of specifications, or even partial or entire articles.
With the right data and a properly configured NLG template, you can leave some types of content creation to the machines while humans create other types of content and double down on promotion.
NLG technology and NLG models are used across a range of contexts.
Today, NLG systems can write email subject lines, snippets of blog posts, summaries of in-depth reports, short-form advertising copy, chatbot responses, and much, much more.
NLG is a sub-field of natural language processing (NLP), which is also a type of AI.
What is the difference between NLG and NLP?
Natural language generation (NLG) and natural language processing (NLP) are two processes that often go hand in hand.
NLG is the process of generating natural language text, while NLP is the process of understanding natural language. NLG can be seen as a subset of NLP, which is why it’s useful to have an understanding of both.
NLP is the step that occurs before human-readable text can be generated through NLG. As put by NLG provider Narrative Science, "Natural language processing reads while NLG writes" (or speaks).
What is natural language understanding (NLU)?
Another term you'll hear related to NLG is natural language understanding (NLU).
Natural language understanding is a subset of NLP. It's a field of artificial intelligence that is dedicated to the development of computational models which can interpret the meaning behind human language.
The ultimate goal of this research is to create a system that can understand and respond to human speech in a way that is indistinguishable from human cognition.
NLP is focused on getting the actual data into a structure that a machine can then use for NLG. NLU is the step that comes before this, by extracting the meaning of and relationships between words.
First, you need NLU. Then, you can do NLP. Once you do NLP, you have the ability to use NLG.
Why do we use natural language generation?
Why use NLG at all? To take advantage of its many benefits.
NLG makes it possible to create content at scale. Instead of hand-writing a report, story, or article, a machine can help create it for you—and still sound like human language.
Some advanced NLG even enables auto-generated articles with a narrative structure that sounds like a human wrote it.
It also enables voice assistants and chatbots. With NLG, machines can answer questions and provide assistance via audio or text.
Some NLG can even predict what you're going to say or write next, then complete your sentence for you with a high degree of accuracy.
In daily life, NLG provides serious convenience, since you can now quickly and easily receive lightning-fast responses to natural language queries from a machine.
In consumer life, NLG makes it easier and cheaper to answer questions about products and services, get help with orders, and resolve issues with purchases.
In business and marketing, NLG makes it possible to create content at scale, automate written reports, and provide customer service—all of which can reduce operational costs and increase revenue.
What is an example of NLG?
One common example of NLG is autocorrect.
The AI systems that power your phone understand when human language is correct or incorrect, then automatically generate the correct language in a text message, email, or document.
Any machine system that automatically generates language is likely using some version of NLG.
GPT-3 is one of the most popular NLG text generation models used today. GPT-3 stands for Generative Pre-Trained Transformer 3, and it was released in 2020.
The model is trained on 175 billion parameters and is 10 times more powerful than the models which came before it. It's increasingly used to generate text that is nearly indistinguishable from human-written sentences and paragraphs.
In business and marketing, there are numerous examples of NLG.
NLG systems can produce short-form, long-form, or summarized text.
In the case of Gmail Smart Compose, NLG produces short-form text snippets based on what the system thinks you type next.
Other NLG systems can produce short-form ad copy (including Facebook and search ads) or email subject lines.
NLG can generate long-form text snippets to supplement blog posts or create more substantial written narratives, including written interpretations of performance data.
The technology can also take long-form text and extract shorter summaries of the content, producing briefs and outlines.
Major voice assistants like Apple's Siri and Amazon's Alexa rely on NLG to answer your questions and queries. Any software program or device that speaks back when you speak to it is using some form of NLG.
NLG is used heavily in many chatbot technologies to partially or fully generate natural language responses to use queries.
Sophisticated chatbots use NLG to interpret what you type, then generate responses based on what you say.
This may include customizing language based on your query or tone or offering specific messaging depending on the topic.
It may also include answering specific questions you ask by extracting content from areas of the website and packaging it into a response.
Combining some of the capabilities above, some automated lead nurturing tools use NLG.
These tools are AI-powered solutions that automatically respond to leads via email and chat using NLG. This ensures all leads coming into a pipeline receive a response 24/7, whether or not human reps are available.
What are some natural language generation tools?
Thousands of NLG tools now exist, and are used across different consumer and business contexts.
Here at Marketing AI Institute, our specialty is marketing and we track thousands of AI tools for marketing. Here are some of the NLG tools we've found to use for marketing.
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.
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.
What steps should you take to get started with NLG?
You probably already have if you use a smartphone or voice assistant.
But 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.