An Online Encyclopedia that Writes Itself

To be sure, Wikipedia’s Boko Haram entry is clearer. But the BBN system captures everything that appears on news sites—not just on topics people chose to write Wikipedia pages about—and constantly and automatically adds information, says Sean Colbath, a senior scientist at BBN Technologies who demonstrated the technology. “I could go and read 200 articles to learn about Bashar Al-Assad (the Syrian dictator). But I’d like to have a machine tell me about it,” says Colbath. (The system, by the way, picks up the fact that the brutal Al-Assad is also a licensed ophthalmologist.)

It starts by detecting an “entity”—a name or an organization, such as Boko Haram, accounting for a variety of spellings. Then it identifies other entities (events and people) that are connected to it, along with statements made by and about the subject. “It’s automatically extracting relationships between entities,” Colbath says. “Here the machine has learned, by being given examples, how to put these relationships together and fill in those slots for you.”

The Boko Haram page goes on to list associated organizations and statements by and about the group. Clicking on any of them takes you back to original news sources, many of them translations of articles originally published in Arabic by sites such as Al Sharq in Qatar and Al Balad in Lebanon.

The BBN project is the fruit of the Defense Advanced Research Projects Agency’s latest effort to build machines that read as humans do, a decades-old problem that has been the focus of increasing research in recent years. Under DARPA’s research program, prototypes have been built by SRI International and IBM as well as Raytheon BBN. 

Bonnie Dorr, DARPA’s program manager for the project, says the technology incorporates recent improvements in machine reading, enabling it to do a better job of understanding when the same underlying event is described in multiple ways—such as “Joe is married to Sue” and “Sue is Joe’s spouse”—and to determine the sentiment implied in phrases like “really awesome.”

Automatically summarizing text is notoriously tricky given the difficulty of detecting humor, sarcasm, obviously incorrect information, idioms, and variant spellings and syntax, not to mention the problems involved in interpreting and translating information sources in different languages.

Accordingly, many of the system’s results come across as a bit wooden or off-key. The profile of Barack Obama, for example, correctly identifies him as the president of the United States, but then summarizes him this way: “Obama has been described as ‘Nobel Peace Prize winner,’ ‘the only reasonable guy in the room,’ ‘an anti-apartheid campus divestment activist,’ and ‘the most trusted politician in the CR-poll.’ “

At another point it notes, “Obama is married to Michelle LaVaughn Robinson Obama; other family members include Henry Healy, Malia Obama, and Ann Dunham.” (Healy is a distant Obama cousin from Moneygall, Ireland. Obama’s younger daughter, Sasha, isn’t mentioned.)

The system lacks real-world knowledge that would help a human analyst recognize something as false, humorous, or plainly irrelevant. Indeed, some of the outputs can be a little comical. I looked up Abraham Lincoln and found that the statements attributed to him include a number of accurate ones (though nothing from his most famous speech, the Gettysburg Address). Then I stumbled across this quote, which seems to have been produced when the system got itself snagged in some published list of famous sayings and did its best to synthesize them. “Abraham Lincoln says that the point of honey one fishing of flies more than fish barrels of a bitter pill, as well as the case for humans,” the profile reports.

Humans aren’t going to be completely replaced anytime soon.