End-to-end learning of dialogue agents for information access

US10546066B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Lihong Li · Redmond, US
• Bhuwan Dhingra · San Diego, US
• Jianfeng Gao · Woodinville, US
• Xiujun Li · Seattle, US
• Yun-Nung Chen · Bellevue, US
• Li Deng · Redmond, US
• Faisal Ahmed · Round Rock, US

Key dates

• Filing date: Jan 13, 2017
• Grant date: Jan 28, 2020
• Expiry date: Feb 19, 2037

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/044
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Described herein are systems, methods, and techniques by which a processing unit can build an end-to-end dialogue agent model for end-to-end learning of dialogue agents for information access and apply the end-to-end dialogue agent model with soft attention over knowledge base entries to make the dialogue system differentiable. In various examples the processing unit can apply the end-to-end dialogue agent model to a source of input, fill slots for output from the knowledge base entries, induce a posterior distribution over the entities in a knowledge base or induce a posterior distribution of a target of the requesting user over entities from a knowledge base, develop an end-to-end differentiable model of a dialogue agent, use supervised and/or imitation learning to initialize network parameters, calculate a modified version of an episodic algorithm. e.g., the REINFORCE algorithm, for training an end-to-end differentiable model based on user feedback.