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

Опубликовано 27 июля 2016, 23:31

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 determinations are generally invisible to users and in many cases even to the engineers who design them. This talk describes some of the problems that this creates, based mainly on an assessment of our own mistakes; and presents some technologies for providing explicit and visible editorial control in news and media information systems. I�ll also talk about our recent work on automatically generating stories from data based on human editorial judgment. A system based on this technology is already generating more than 10 thousand stories weekly in areas ranging from sports to business. 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.