Facebook’s new research tool is designed to create a truly conversational AI

Most of us talk to our computers on a semi-regular basis, but that doesn’t mean the conversation is any good. We ask Siri what the weather is like, or tell Alexa to put some music on, but we don’t expect sparkling repartee — voice interfaces right now are as sterile as the visual interface they’re supposed to replace. Facebook, though, is determined to change this: today it unveiled a new research tool that the company hopes will spur progress in the march to create truly conversational AI.

The tool is called ParlAI (pronounced like Captain Jack Sparrow asking to parley) and is described by the social media network as a “one-stop shop for dialog research.” It gives AI programmers a simple framework for training and testing chatbots, complete with access to datasets of sample dialogue, and a “seamless” pipeline to Amazon’s Mechanical Turk service. This latter is a crucial feature, as it means programmers can easily hire humans to interact with, test, and correct their chatbots.

Abigail See, a computer science PhD at Stanford University welcomed the news, saying frameworks like this were “very valuable” to scientists. “There’s a huge volume of AI research being produced right now, with new techniques, datasets and results announced every month,” said See in an email to The Verge. “Platforms [like ParlAI] offer a unified framework for researchers to easily develop, compare and replicate their experiments.”

In a group interview, Antoine Bordes from Facebook’s AI research lab FAIR said that ParlAI was designed to create a missing link in the world of chatbots. “Right now there are two types of dialogue systems,” explains Bordes. The first, he says, are those that “actually serve some purpose” and execute an action for the user (e.g., Siri and Alexa); while the second serves no purpose, but is actually entertaining to talk to (like Microsoft’s Tay — although, yes, that one didn’t turn out great).

“What we’re after with ParlAI, is more about having a machine where you can have multi-turn dialogue; where you can build up a dialogue and exchange ideas,” says Bordes. “ParlAI is trying to develop the capacity for chatbots to enter long-term conversation.” This, he says, will require memory on the bot’s part, as well as a good deal of external knowledge (provided via access to datasets like Wikipedia), and perhaps even an idea of how the user is feeling. “In that respect, the field is very preliminary and there is still a lot of work to do,” says Bordes.

It’s important to note that ParlAI isn’t a tool for just anyone. Unlike, say, Microsoft’s chatbot frameworks, this is a piece of kit that’s aimed at the cutting-edge AI research community, rather than developers trying to create a simple chatbot for their website. It’s not so much about building actual bots, but finding the best ways to train them in the first place. There’s no doubt, though, that this work will eventually filter through to Facebook’s own products (like its part-human-powered virtual assistant M) and to its chatbot platform for Messenger.

Yann LeCun, head of AI research at Facebook, says that progress is already happening and that users will see “continuous improvement” to chatbots of all stripes. He gives the example of systems that are capable of digesting large datasets — like Wikipedia or scientific journals — and answering questions on them. Until recently, these didn’t even exist, but now this sort of tech will be coming online “relatively soon.” This sort of functionality could be key to the future of Facebook’s AI platform, says LeCun.

“Ultimately one of the objectives of this is to have your own digital friend; your virtual assistant that is customized for you,” he says. “It mediates your interaction with the digital world — perhaps with your friends and other people — and helps you out through the incredible amount of information we are bombarded with every day, and helps us with our daily lives.”

If this sounds familiar, it might be because Google outlined a very similar vision last October at its Pixel phone unveiling. Like Facebook, the search giant wants to build truly personal assistants that are trained on each individual’s data, and that can act as go-betweens with the wider digital world. For either company’s plan to work, they’ll need bots that we’re comfortable talking to. ParlAI should help the conversation flow.