Amazon Technologies, Inc.

Anthony Bissell

Janet Louise Slifka

Pragati Verma

Christopher Alan Wheeler

Emma Rose Hathaway

Cedric Warny

Susanna Rose Young

Skye Loren Huerta

Jean-Michel Caruge

Dustin Edward Axman

Akhil Chandrashekhar Acharya

Reda Yacouby

A natural language processing system may select a synthesized speech quality using user profile data. The system may receive a natural language input and determine responsive output data. The system may, based at least in part on user profile data associated with the input, determine response configuration data corresponding to a quality of synthesized speech. The system may then determine further output data for presentation using the responsive output data and response configuration data.

Dynamic system response configuration

A natural language processing system may use system response configuration data to determine customized output data forms when outputting data for a user. The system response configuration data may represent various output attributes the system may use when creating output data. The system may have a certain number of existing profiles where a profile is associated with certain settings for the system response configuration data/attributes. The system may also use various data such as context data, sentiment data, or the like to customize system response configuration data during a dialog. Other components, such as natural language generation (NLG), text-to-speech (TTS), or the like, may use the customized system response configuration data to determine the form, timing, etc. of output data to be presented to a user.

Example embodiments provide techniques for configuring a natural-language processing system to perform a new function given at least one sample invocation of the function. The training data consisting of the sample invocation may be augmented by determining which subset of available training data most closely resembles the sample invocation and/or function. The effect of re-training a component this this augmented training data may be determined, and an annotator may review any annotations corresponding to the invocation if the effect is large.

Natural language processing

Systems and techniques for generating natural language understanding (NLU) models are described. A developer of an NLU model may provide data representing runtime NLU functionality. For example, a developer may provide one or more sample natural language user inputs. The NLU model generation system may expand data, provided by the developer, to result in a more robust NLU model for use at runtime. For example, the NLU model generation system may expand sample natural language user inputs, may translate sample natural language user inputs into other languages, etc. The present disclosure also provides a mechanism for transitioning between using NLU models of a first NLU model generation system and NLU models of a second NLU model generation system.

Natural language understanding model generation

Example embodiments provide techniques for configuring a natural language processing (NLU) system for new functionalities using sample user inputs provided by a developer. The system may determine intent labels associated with the sample user inputs using previous user inputs previously processed by the NLU system. The system may configure a new NLU model, using the NLU model associated with the intent label determined by the system, where the new NLU model is configured to enable invocation of the new functionality.

Growing community of inventors

Somerville, MA, United States of America

Anthony Bissell