Alexa Conversations To Get More Natural

Amazon has announced the launch of Alexa Conversations, a new deep learning-based approach that developers can use for creating natural voice experiences on Alexa with less effort, fewer lines of code, and less training data.

“This new model helps developers create natural, flexible dialogs within a single skill and in the upcoming releases brings multiple skills into a single conversation,” Drew Meyer wrote in a blog post.

With users asking Alexa for help with more sophisticated tasks, such as ride booking, shopping, ticket purchasing or making reservations, they want to be able to speak with Alexa fluidly across multiple topics. Meyer noted that the eCommerce giant would like to see Alexa learn to predict a customer’s true goal from the direction of the dialog and offers up the appropriate skills through Alexa Conversations.

Currently available in developer preview in the U.S., the tool combines an AI-driven dialog manager with an advanced dialog simulation engine that automatically generates synthetic training data.

“Alexa Conversations helps you quickly create interactions that are more conversational, and not forced into strict patterns or sequential workflows. In the past, developers scripted every potential turn, built an interaction model, managed dialog rules, wrote back-end business logic, and analyzed logs to test and iterate. For example, the Atom Tickets skill used 5,500 lines of code and nearly 800 training examples,” explained Meyer.

“Now, you provide dialog samples and Alexa Conversations predictively models the dialog path using a deep, recurrent neural network. At runtime this neural network takes the entire session’s dialog history into account and predicts the optimal next action or step in the dialog, improving accuracy and reducing your design and code efforts. It is trained to interpret dialog context in order to handle multiple user workflows, accommodate natural user input (like out-of-sequence information or corrections), address common business transaction errors, and proactively recommend additional API functionality. The Atom Tickets skill built with Alexa Conversations shrank almost 70%, to just 1,700 lines or code, and needed only 13 customer dialog samples,” he added.