“Thousands of other abilities contribute to our intelligence, but the use of language as a means of communicating complicated ideas trumps them all.”- Practical Artificial Intelligence for Dummies
Here are answers to top five questions regarding natural language generation (NLG).
1. What is Natural Language Generation?
Natural Language Generation (NLG), a subfield of artificial intelligence (AI) which produces language as output on the basis of data input, is not a new concept. What is new, however, is the increase in adoption of NLG into the enterprise. There are a plethora of ways the technology is being employed, primarily to improve human productivity, customer engagement and operational efficiency.
2. What’s the goal of NLG?
People have always communicated ideas from data. But with the explosion of data that needs to be analyzed and interpreted, coupled with increasing pressures to reduce costs and meet customer demands, the enterprise must find innovative ways to keep up. As it turns out, a machine can communicate ideas from data at extraordinary scale and accuracy. And it can do it in a particularly articulate manner. When a machine automates the more routine analysis and communication tasks, productivity increases and employees can focus on more high value activities.
As stated in the book, "Practical Artificial Intelligence for Dummies":
“The goal of natural language generation (NLG) systems is to figure out how to best communicate what a system knows. The trick is figuring out exactly what the system is to say and how it should say it. Unlike NLU (Natural Language Understanding), NLG systems start with a well‐controlled and unambiguous picture of the world rather than arbitrary pieces of text. Simple NLG systems can take the ideas they are given and transform them into language. This is what Siri and her sisters use to produce limited responses. The simple mapping of ideas to sentences is adequate for these environments.”
3. How is NLG different than NLP ?
Gartner’s recent Hype Cycle for BI and Analytics sums up the difference between NLG and NLP (Natural Language Processing) well:
“Whereas NLP is focused on deriving analytic insights from textual data, NLG is used to synthesize textual content by combining analytic output with contextualized narratives.”
In other words, NLP reads while NLG writes. NLP systems look at language and figure out what ideas are being communicated. NLG systems start with a set of ideas locked in data and turn them into into language that, in turn, communicates them.
4. What are the different variations of NLG?
A recent report from CITO Research, “The Automated Analyst: Transforming Data into Stories with Advanced Natural Language Generation” outlines the different types of NLG.
“The simplest level of NLG takes a few data points and turns them into sentences. A simple weather report example is a sentence like this: “the high today will be 72 degrees.” The next level of NLG takes a templated paragraph and generates language based on the changing data. Sports scores often can be handled this way. For certain types of template reports, this works. The analytics performed by such systems isn’t very sophisticated (it’s generally driven by business rules framed as if/then statements). Advanced NLG transforms data into a narrative with a beginning, middle, and end. This narrative, or story, is based on an in-depth analysis of the data.”
5. What is the business impact of NLG and where can it be integrated?
Back to Gartner’s 2015 Hype Cycle on BI & Analytics:
“NLG is already being used effectively to reduce the time and cost of conducting repeatable analysis and writing reports on data for required operational and regulatory report automation, in financial services (earnings reports), government (benefits statements or weather forecasts) and in advertising (personalized messages).”
As for integration, NLG works nicely alongside data discovery and visualization platforms, generating an accompanying narrative to explain the context of the insights being discovered. Gartner continues:
“While NLG supports a number of productivity-enhancing use cases outside of analytics, the combination of NLG with automated pattern detection and self-service data preparation has the potential to drive the user experience of next generation smart data discovery platforms, and expand the benefits of advance analytics to a wider audience of business users and citizen data scientists.”
For more information on NLG, be sure to read the recent report from CITO Research, “The Automated Analyst: Transforming Data into Stories with Advanced Natural Language Generation”