From Contextual Search to Automatic Content Generation: Scaling Human Editorial Judgment

Systems that present people with information inescapably make editorial judgments in determining what information to show and how to show it. However the editorial values used to make these judgments are generally invisible to users and in many cases even to the engineers who design them. Our work is aimed at developing news and media information technologies that provide explicit and visible editorial control, at scale, and at all stages of the process of determining what information to present and how to present it.

Some of our most exciting work in this area is aimed at automatically generating stories from data using human-authored editorial models. A system based on this technology is already generating more than 10 thousand stories weekly in areas ranging from sports, to business, to politics. This system is the nation's most prolific and published author of, among other things, women's collegiate softball stories. The stories compare favorably to those written by human beings.