Amazon Technologies, Inc.

Bigyan Rajbhandari

Chenlei Guo

Abhinav Sethy

Alireza Roshan Ghias

Pragaash Ponnusamy

Praveen Kumar Bodigutla

Zhenxiang Zhou

Karen Catelyn Stabile

Kevin Quinn

Ruhi Sarikaya

Kai Chieh Liu

Xiaohu Liu

Joe Pemberton

Zheng Du

Zhenyu Yao

Hung Tuan Pham

Sriharsha Venkata Chintalapati

Techniques for performing centralized unsuperivised learning in a multi-domain system are described. A user may request labeled data for an ML task, where the request includes a prompt for obtaining relevant explicit user feedback. The system may use the prompt to collect explicit user feedback for relevant runtime user inputs. After a duration of time (in the user's request for labeled data) has elapsed, the system determines whether collected user feedback indicates processing of the user input was defective and, if so, determines a cause of the defective processing. The system then uses one or more label generators to generate labeled data using the collected user feedback, whether the processing was defective, and the determined defect cause.

Machine learning label generation

Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed. If the trained machine learning model(s) indicates the present ASR output text data corresponds (or substantially corresponds) to such previous ASR output text data, the system may rewrite the present ASR output text data to correspond to text data representing a rephrase of the user input that will (or is more likely to) result in a correct action being performed.

Learning how to rewrite user-specific input for natural language understanding

Growing community of inventors

Kirkland, WA, United States of America

Bigyan Rajbhandari