Amazon on Monday announced the general availability of Alexa Conversations, a deep learning-powered dialog manager for the Alexa Skills Kit. The tool, first previewed in 2019, helps developers create more natural conversations with customers.
“Natural language is actually a very difficult thing to emulate,” Nedim Fresko, a spokesperson for Amazon’s Alexa Devices and Developer Technologies, told ZDNet last year. “When people speak naturally, they change the subject and make contextual references to things they’ve said. Sometimes they over-deliver information and other times they omit it — that’s something that developers.”
To use Alexa Conversations, developers give Amazon some sample sentences of their conversations, as well as some APIs that implement the services they’re trying to acquire. From these samples, Amazon’s AI system tries to predict all the possible conversations the user might have. It reduces the amount of back-end code that developers have to create and the amount of training data they have to provide.
Since its launch and transition to beta, thousands of developers have tested Alexa Conversations, including major commercial brands like iRobot.
Based on beta feedback, Alexa Conversations now has improved error messages, as well as dialog cloning, new command line interface support, and improved authoring workflows.
Information source: zdnet.com
