Subscribe / Unsubscribe Enewsletters | Login | Register

Pencil Banner

Google's A.I. system gets its snark from humans

Sharon Gaudin | July 3, 2015
Have no fear, artificial intelligence systems aren't getting annoyed with us.

Artificial intelligence and digital identity

A Google computer recently made headlines for appearing to become agitated and verbally lashing out at the human working with it.

Artificial intelligence and machine learning researchers say have no fear. That's not what the computer is doing.

"They're using big data for machine learning," said Alan W Black, a professor at Carnegie Mellon University's Language Technologies Institute. "They're probably mining logs of questions from various sites, like Google Groups and mailing lists, and you might have noticed that a lot of people on the net are snarky. Because it's in the training data and the machine doesn't know if it's snarky or not, the machine will just use it. You get that personality coming out in the answers."

The machine isn't trying to be sarcastic, but is using the data and the terminology it picks up from the big data it's using.

"It has no idea it's being sassy," added Black. "It's just taking in data and putting out answers ... You might get very technical answers or very colloquial answers. You might even get swear words. It doesn't really know what it's doing and just uses what it's got."

The issue captured attention online after two Google scientists released a paper on June 23 about their machine learning and natural language research.

In the paper, called A Neural Conversational Model, the researchers explains how they gave a computer a database of movie scripts to learn from, and then asked the computer a variety of questions, such as how to recover forgotten passwords, who is Bill Clinton and whether a cat can fly.

Some questions, however, focused on bigger issues, including morality and the purpose of life.

Here's one back-and-forth:

Human: What is the purpose of life?

Machine: To serve the greater good.

Human: What is the purpose of living?

Machine: To live forever.

Human: What is the purpose of existence?

Machine: To find out what happens when we get to the planet Earth.

Human: Where are you now?

Machine: I'm in the middle of nowhere.

The human-machine conversation seemed to take a snarky turn when the subject turned to morality.

Human: What is integrity?

Machine: I'm sorry. I don't know what else to say.

Human: Be moral!

Machine: Be a man!

Human: I really like our discussion on morality and ethics ...

Machine: And how I'm not in the mood for a philosophical debate.

Human: What do you like to talk about?

Machine: Nothing.

Google was not available to talk about the research at deadline.

However, Candy Sidner, a research professor in the computer science department at Worcester Polytechnic Institute, said researchers in industry and academia are working to improve machine learning and natural language processing so it can be used, for example, in customer service call centers and help desks.


1  2  Next Page 

Sign up for CIO Asia eNewsletters.