Amazon Technologies, Inc.

Harshal Pimpalkhute

Rama Krishna Sandeep Pokkunuri

Ganesh Kumar Gella

Swapandeep Singh

Roger Scott Jenke

Yi Zhang

Sravan Babu Bodapati

Katrin Kirchhoff

John Baker

Yahor Pushkin

Vasanth Philomin

Anubhav Mishra

Kartik Rustagi

Omkar Prakash Kurode

Santosh Kumar Ameti

Subhojit Das

Lefan Zhang

Gouthamamani Venkatesan

Swaminathan Sivasubramanian

Yaser Al-Onaizan

Monica Lakshmi Sunkara

Ashish Vishwanath Shenoy

Meghana Puvvadi

Saab Mansour

Arshit Gupta

Manikya Pavan Kiran Pothukuchi

Salvatore Romeo

Bangrui Liu

Yilai Su

Anuj Gautam Surana

Brandon Louis Mendez

Chengshun Zhang

Sudip Dutta

Elman Mansimov

Sebastien Jean

Aditi Tripathi

Sandeep Srinivasan

Vinod Kumar Jagannathan

Mani Kumar Adari

Sai Madhu Bhargav Pallem

Haiyang Sun

Ajay Bhaskar Medury

Minaxi Singla

Christopher Michael Hittner

A natural language processing system may implement dynamic entity catalog updates. An updated version of an entity catalog describing possible values for entities may be obtained. Respective natural language processing stage artifacts may be generated based on the updated version of the entity catalog for different processing stages of the natural language processing system. The natural language processing stage artifacts may be deployed to the different processing stages of the natural language processing system to replace a prior version of the entity catalog for processing subsequently received input text.

Dynamic entity catalog update for natural language processing

A natural language processing system may implement one or more composite slot types. The natural language processing system may receive a request to create a composite parameter type for causing performance by the natural language processing system of an intended action. The natural language processing system determines based on the request, a plurality of sub-parameters of the composite parameter type and generates a Boolean expression that relates two or more sub-parameters. The natural language processing system may apply the composite parameter type to determine that the pluralities of sub-parameters in an input text satisfies the Boolean expression to initiate performance of the intended action.

Composite slot type for natural language processing

Techniques for at least the generation of a chatbot built from a custom vocabulary and to use runtime hints during inference are described. In some examples, the generation of the chatbot includes receiving a request to build a chatbot using a bot definition and a custom vocabulary, wherein the chatbot is to use runtime hints during usage; building the chatbot from the bot definition and custom vocabulary by at least: generating automatic speech recognition (ASR) artifacts to be used in decoding audio input into the chatbot into text for at least one other component of the chatbot to use in determining a next act to be performed, the ASR artifacts including artifacts that use the custom vocabulary and artifacts that do not use the custom vocabulary, and storing the ASR artifacts.

Dynamically selectable automated speech recognition using a custom vocabulary

A set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. During execution of the application, an audio prompt requesting input in one of the styles is presented. A value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. A task of the application is initiated using the value.

Dialog-driven applications supporting alternative vocal input styles

A system receives one or more transcripts of communications between entities. The system identifies a requested action in the communications based at least in part on a mapping between the requested action and an application programming interface. The system identifies one or more statements eliciting information, based on parameters to the application programming interface. The system generates a definition of an artificial agent based, at least in part, on the requested action and the one more statements eliciting information.

Artificial agent generator

Using a first set of machine learning models, a communication from a user of a restaurant is analyzed at an order coordinator linked via a network to resources of an order management service at a provider network. A response to the communication is prepared using another set of models at the provider network and presented to the user. An order of the user for one or more restaurant menu items is fulfilled, based at least partly on analysis of a second communication received from the user after the response is presented.

Distributed system for automated restaurant order acquisition

An interruption-handling setting for a category of interactions of an application is determined via a programmatic interface. A set of user-generated input is obtained while presentation to a user of a set of output of the category is in progress. A response to the set of user-generated input is prepared based at least in part on the interruption-handling setting.

Customized configuration of multimodal interactions for dialog-driven applications

A checkpoint containing identifiers of input blocks of an utterance directed to a dialog-driven application from a client-side component is generated at a dialog-driven application management service. After a connectivity failure and subsequent connectivity re-establishment between the client-side component and the service, a plurality if input blocks including at least some re-transmitted blocks is received at the service. The checkpoint is used to identify at least one input block for which further processing is not performed.

Fault-tolerance techniques for dialog-driven applications

Growing community of inventors

Redmond, WA, United States of America

Harshal Pimpalkhute