Artificial Intelligence

Uber Debuts Conversational AI Dev Platform

Uber Releases Open-Source Conversational AI Platform Called Plato

Uber AI, the ride-hailing company’s artificial intelligence division, has released an open-source AI platform called the Plato Research Dialogue System, according to a report by Venturebeat

The platform is made to build, train and deploy conversational AI agents for people to gather data from both prototypes and demonstration systems. 

“Intelligent conversational agents have evolved significantly over the past few decades, from keyword-spotting interactive voice response (IVR) systems to the cross-platform intelligent personal assistants that are becoming an integral part of daily life, Uber said in a blog post. “Along with this growth comes the need for intuitive, flexible, and comprehensive research and development platforms that can act as open testbeds to help evaluate new algorithms, quickly prototype, and reliably deploy conversational agents.”

The artificial intelligence platform supports speech, text and dialogue interactions and each agent can communicate with humans, data or other agents. It can also use pretrained models for each component of a conversational agent, as well as each component having the ability to be trained during data interactions. 

The platform separates data processing into seven steps: speech recognition, language understanding, state tracking, API calls, generation of language policies regarding dialogue and synthesis of speech. 

Plato also handles data logging by keeping track of events in what’s called the Dialogue Episode Recorder. The recorder has information about previous dialogue states, what actions were taken and also current dialogue states.

“We believe that Plato has the capability to more seamlessly train conversational agents across deep learning frameworks, from Ludwig and TensorFlow to PyTorch, Keras, and other open source projects, leading to improved conversational AI technologies across academic and industry applications,” wrote Uber AI researchers Alexandros Papangelis, Yi-Chia Wang, Mahdi Namazifar and Chandra Khatri. “[We’ve] leverage[d] Plato to easily train a conversational agent how to ask for restaurant information and another agent how to provide such information; over time, their conversations become more and more natural.”



About: Accelerating The Real-Time Payments Demand Curve:What Banks Need To Know About What Consumers Want And Need, PYMNTS  examines consumers’ understanding of real-time payments and the methods they use for different types of payments. The report explores consumers’ interest in real-time payments and their willingness to switch to financial institutions that offer such capabilities.