Uber now has an artificial intelligence platform for developers. The company just announced its Plato Research Dialogue System. The system is a platform for developing, training and deploying AI-driven conversational agents.
Uber built the platform with many developer types in mind. From those who have no experience with conversational AI to experts, Uber utilized a clean and consistent framework that should enhance accessibility. Uber compares Plato to Olympus, PyDial, ParlAI, the Virtual Human Toolkit, Rasa, DeepPavlov, and ConvLab.
Deploying a conversational agent through the platform follows a seven-step process similar to many AI platforms:
- Speech recognition (transcribe speech to text)
- Language understanding (extract meaning from that text)
- State tracking (aggregate information about what has been said and done so far)
- API call (search a database, query an API, etc.)
- Dialogue policy (generate abstract meaning of agent’s response)
- Language generation (convert abstract meaning into text)
- Speech synthesis (convert text into speech)
Additionally, Plato supports a number of third-party AI architectures. This gives developers the ability to train across platforms to enhance agent learning. Agents can be trained online or offline using any machine learning library (e.g. TensorFlow, PyTorch, etc.). Check out the docs on GitHub to learn more.