What is: natural language generation (NLG)?
20 April 2020
Saying the right words in the right order and conveying a clear message that can be easily understood is a tricky business. For a machine, which processes information in an entirely different way than the human brain does, it can be trickier still.
Solving this issue has is the mission of natural language generation (NLG).
You may not realize it, but NLG has begun to manifest in many areas of our lives. From our chats with virtual assistants like Siri and Alexa, to our interactions with the chatbots and tech support of our favorite brands, NLG has begun to play an increasingly important role in our typical day.
So what exactly is natural language generation?
Human language is complex.
There are approximately 6,500 distinct languages spoken worldwide. For our purposes, we are going to zero in on the English language and NLG efforts focused on English. Although English has a comparatively small number of native speakers worldwide (estimated to be about 400 million), it is spoken as a secondary language by as many as 1.6 billion people worldwide.
According to the Oxford English Dictionary (OED), it contains full entries for 171,476 words in current use, and 47,156 obsolete words. To this may be added around 9,500 derivative words included as subentries. And these figures don’t take account of entries with senses for different word classes (such as noun and adjective). This suggests that there are, at the very least, a quarter of a million distinct English words.
That’s a lot of words.
Natural language generation is complex
With so many variables to choose from, there are literally billions of ways that any series of words can be strung together to convey a message. Add the English language’s grammar rules (which are also complex), and you’ve got yourself a very interesting mathematical problem.
Natural language generation is the process of developing a learning machine capable of sorting through all these variables and putting them together into natural, human-sounding sentences, statements, or paragraphs without intervention from the handler.
To accomplish this massive feat, developers have leaned heavily on the computing principle of the algorithm. Algorithms are purpose-built computer programs capable of sorting through large sets of data and reordering that data according to a predetermined set of objectives. In the case of natural language generation, such algorithms focus on the way human language is structured and sort through all the available words in an attempt to artificially replicate human language patterns.
Phrasee is complex
Here at Phrasee, we have been working in the field of natural language generation for marketing for years. We have encountered first-hand the problems associated with sentence structure, tone of voice, and brand voice that are a natural side effect of developing technology like natural language generation for marketing language.
But, as we have learned through an exhaustive process of trial and error (and a whole lot of research and experimentation), delivering human-sounding, high-performing results is entirely possible. We call it Brand Language Optimization, and if you want to learn more, you can do that here.
Want to know more about using AI in your marketing?
Check out our Learning Hub for everything you’ll need to know!
You may also like:
We've partnered with Braze to eEnable seamless optimization of language across digital channels. Get the scoop.
06 May 2021
Phrasee enters $8.5 Billion Customer Experience (CX) Market with First Technology to Optimize Brand Language in Real-Time
Phrasee announces the appointment of four new members of the leadership team, as demand for AI-Powered Copywriting continues to rise.
15 Apr 2021
We catch up with Jasper Pye, VP, Product at Phrasee, and John Galvin, Manager, Solutions Consulting EMEA at Cheetah Digital to find out more about the new Phrasee X Cheetah Digital integration from the experts that know it best!
09 Mar 2021
Hi. We’re Phrasee. And we make people money. How much money? If only there were some kind of tool where you could put in a few numbers about the performance of your email marketing program and then you’d click a button and get some kind of answer to that question! Oh wait! Find out what Phrasee could make for you.
04 Feb 2021
With key email marketing performance metrics in decline industry-wide, finding ways to boost email marketing ROI is an important strategic goal for brands in 2021. Here’s how to buck the trend and improve your brand’s email marketing ROI in a rapidly shifting consumer landscape.
27 Jan 2021
Travel has been in a tricky place but all indications, it seems, point to travel brands breaking out of the marketing holding pattern that they’ve been in, in the coming weeks and months. We’ve spent some serious time thinking about what our friends in the travel industry can do right now to prepare for the post-COVID-19 rebound to come.
21 Jan 2021
With 2021 just around the corner, is your email marketing strategy ready? From personalization to segmentation and optimization to tracking, we share best practices for building an effective email marketing strategy.
16 Dec 2020
This year, we are continuing our tradition and sending more bags of kindness to those in need. Find out more about why we're supporting the incredible cause that is Kindness Bags.
16 Dec 2020