Sunday, June 26, 2016

Artificial Intelligence Algos To Read, Understand and Comment On News Stories

This seems efficient.
Combine the story-writing programs* with the commenting programs and just cut the humans out completely.
From New Scientist, June 20:

AI just got a big boost in its ability to understand the news
Soon you could be chatting with your computer about the morning news. An AI has learned to read and answer questions about a news article with unprecedented accuracy.

Creating AI systems that can learn in the background from humanity’s existing stores of information is one of the big goals of computer science. “Computers don’t have the kind of general knowledge and common sense of how the world works [from reading] about things in novels or watch[ing] sitcoms,” says Chris Manning at Stanford University.

To get a step closer to this, last year, Google’s DeepMind team used articles from the Daily Mail website and CNN to help train an algorithm to read and understand a short story. The team used the bulleted summaries at the top of these articles to create simple interpretive questions that trained the algorithm to search for key points.

Now a group led by Manning has designed an algorithm that beat DeepMind’s results by an impressive 10 per cent on the CNN articles and 8 per cent for Daily Mail stories. It scored 70 per cent overall.

The improvement came through streamlining the DeepMind model.  “Some of the stuff they had just causes needless complications,” says Manning. “You get rid of that and the numbers go up.”

 Design trade-off
“It makes sense,” says Robert Frederking of Carnegie Mellon University in Pittsburgh. “Making something more complicated doesn’t make it better.”

There’s a trade-off in AI design: if an algorithm is complex, it’s more powerful, but to perform well it needs more data to learn from, says Frederking. Simpler AI can train quickly with smaller amounts of data.

Manning says there’s not much more a computer can learn from this particular data set. To prepare the hundreds of thousands of articles for AI readers, DeepMind used a program to go through them and assign the same label to nouns and the pronouns that reference them. But this program inevitably confused some pronouns. Fresh nouns and pronouns labelled in a new data set would be needed to keep AI reading improving.

The advantage of using Daily Mail and CNN articles was that there’s so many of them, says Julia Hockenmaier at the University of Illinois at Urbana-Champaign....MORE
According to the Financial Times' "MailOnline and the next page for the ‘sidebar of shame’" The MailOnline pumps out 750 stories per day.

* We have quite a few links in "Robot Writing Moves from Journalism to Wall Street".