Amazon Technologies, Inc.

Xinhong Zhang

Melanie C B Gens

Rahul Gupta

Sachin Midha

Anoop Kumar

Sriram Venkatapathy

Pavel Bhowmik

Pooja Sanjay Sonawane

Samuel Harry Ingbar

Gokhan Tur

Chenlei Guo

Xing Fan

Shubham Katiyar

Narendra Gyanchandani

Wael Hamza

Puyang Xu

Md Humayun Arafat

Jwala Dhamala

Jennifer Yuen

Dewan Muhammed Ibtesham

Techniques for processing with respect to a user input as contextual information is available are described. A system generates a first task prediction using first context data that is available when a user input is received. The system generates a second task prediction (e.g., updated first task prediction) when second context data is received, and then further generates a third task prediction when third context data is received. Example first context data may include device type information, time information, location, etc. Example second context data may include automatic speech recognition (ASR) data. Example third context data may include natural language understanding (NLU) data. Using the third task prediction, the system generates an output responsive to the user input.

Natural language processing system

Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.

Evaluating natural language processing components

Techniques for tuning parameters for machine learning models are described. Different values for a parameter are tested to determine the value that results in an optimized model. A parameter value may be selected for testing using a search algorithm based on how the model performs with respect to other values for the parameter. Different values may be tested until a stopping criterion (such as time for testing, number of trials, amount of enhancement in performance, etc.) is met. In some embodiments, the techniques may be used to determine parameter values for natural language processing models.

Model configuration

Growing community of inventors

Mercer Island, WA, United States of America

Xinhong Zhang