Internet giants seem to be very excited about chatbots. The promise they make is that in the coming years, you’ll chat with Internet services in much the same way you now chat with friends and family. Cool, huh? Bots will instantly answer questions, respond to requests, and even anticipate your needs.
But a major challenge still remains: building chatbots that can actually chat. Machines can mimic conversation in some ways, but they’re still a long way from really grasping the way humans talk.
Late last month, Google open sourced one of the tools it uses for natural language understanding. This week, Facebook announced DeepText, an AI engine it’s building to understand the meaning and sentiment behind all of the text posted by users to Facebook. In a blog post, Facebook said that it was building the system to help it surface content that people may be interested in, and weed out spam.
Facebook is not yet open sourcing this technology. And the company is only beginning to use DeepText with its own services. But this goes to show how the future is about accelerating the progress of natural language understanding with the aim to rely far less on humans, and far more on data.
This might sound like a minor improvement, but it actually has the potential to transform the social network most of us use every day into a powerful search engine.
“We want DeepText to be used in categorizing content within Facebook to facilitate searching for it and also surfacing the right content to users,” Hussein Mehanna, an engineering director at Facebook’s machine learning team, told the guys over at Quartz.
The universe of that search may not be the whole worldwide web that Google crawls, but it’s still massive. There are over a billion people who check Facebook every single day, and the network has trillions of status updates, event invitations, photo albums, and videos on its servers. Facebook is sitting on an ever-growing mountain of information that it can use more effectively to connect people with similar interests, sell more ads, and help people find things they’re looking for.
Facebook already uses demographic information shared by users, but right now, the majority of the text-based information on Facebook’s servers is unstructured, meaning Facebook doesn’t know users’ intent in posting, or even what users meant. DeepText will help categorize and provide meaning for all that text, and could turn all that unstructured data into information it can use—and users can search. “If we can understand text, we can help people connect and share in a lot of different ways,” Mehanna said.