Good vs. Bad Automated Content? It's In the Context Layer

8.28.17

The difference between good automated content and bad automated content can be boiled down to the number of scenarios the programmer creates to turn ordinary data into beautiful prose.

Data variability, which is predicated upon the number and the depth of insights driven by changes in the data, is the key quality driver in Natural Language Generation (NLG). And to do NLG data variability right, you have to create a lot of scenarios.

NLG creators must always be asking: How vast is the universe of outcomes that the engine takes into account when creating a narrative?

In other words: How many ways can you say something?

It's not a coincidence that this is the same approach used when developing NLG's reverse twin, Natural Language Processing (NLP).

Words from Data meets Data from Words

People get touchy when you confuse NLG and NLP, especially those people who do either for a living (which is not a lot of people, but they still get touchy). The truth is that there is a lot of commonality between NLG and NLP. The core concept is the same: Understand the input and translate to the output.

While NLP takes in words and translates those words to data, NLG takes in data and translates that data to words. But creating words isn't the hard part of NLG. In fact, we've reached the point where machines can create complex sentences without too much trouble. In its simplest form, creating words from data is a binary proposition:

read the rest at: https://automatedinsights.com/blog/good-vs-bad-automated-content-its-in-the-context-layer




Let me know what you thought about this article, good or bad.

Your Email Address

Leave it blank to be anonymous



Your Thoughts?





The Fine Line Between Love and Hate in Startup
Last week, we discussed whether or not Teaching Startup should have a future.

Ideas and money falling out of pockets on Sand Hill Road
There's a lot of debate in this episode and it's all warranted and it's all around where you start your company and how much that matters.

Why Startup is a New and Different Kind of Fun
Before I started my journey at Automated Insights, I had spent a couple years consulting. But I didn't just do consulting, I went all-in on a consulting startup.

Why I Wanted MATI Energy and Neuro Plus on The Startup Show
There are some obvious reasons why I wanted to get Tatiana Birgisson, founder of Mati Energy, and Jake Stauch, founder of Neuro Plus, on The Startup Show. And also some not-so-obvious reasons.

Why That Startup Side Project Is So Important
I realize how cool it is that I'm in a position where I can be so open about my side project(s) at any given time.