What is: natural language generation (NLG)?

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.