Narrative Science, The Robotic Content Farm, Is Looking At More LanguagesBy: Chris Crum - February 23, 2012
Have you read about Narrative Science? This is a company that is creating web articles using computers. We’ve referenced them on more than one occasion as a “robotic content farm”. It makes you wonder where we’re headed in terms of web content? Will our jobs become obsolete as the content machines rise or will that human element always be needed?
Last week, we saw where Narrative Science has a project in which its machines are creating readable stories from tweets. It showed off an example about Newt Gingrich getting attention with “hot-button topics”. It wasn’t a mind-blowing piece of writing, but it was certainly passable for human, and even better than some content I’ve seen from some humans. I can only assume the technology will get better at what it does.
Today, co-founder and CTO Kris Hammond took to his blog to discuss the obstacles of the Narrative Science approach to translation and creating content in different languages. Hammond wrote (assuming a robot isn’t ghostwriting for him):
Multi-lingual generation of content from data has always been on Narrative Science’s road map and has informed the modularization of the core platform. It is only after all of the analysis of the facts, evaluation of their importance, and the composition of the representation that the system generates language. Within this model, generating in Spanish, Japanese, German, etc. is no different than generating in English.
The system is not designed to translate, but to generate in multiple languages.
In general, we are not ready to do this, mostly because of the composition of our client base, but doing so is a matter [of] pulling in native speakers who know how to write in non-English languages to configure the platform for the new language.
So, what I take away from this is that while Narrative Science may not be ready to go multi-lingual just yet, it’s more than likely going to happen in the future. So the machines taking over writing won’t be limited to just English.