Amazon Technologies, Inc.

Abhijit S Barde

Rashmi Gangadharaiah

Brijesh Luckria

Deepak Seetharam Nadig

Jonathan James Pezzino

Sopan Khosla

Sandesh Swamy

Fawad Abbas

Bhaskar Hosahalli Rangaswamy

Siddharth Satish Goyal

Erik Nathaniel Haukenes

Karanpaul Singh Chawla

Bhaskar Hosahalli Hosahalli Rangaswamy

Michael W Miller

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

Processing natural language queries for network-based services

Techniques for a system to automatically recommend supported actions to a notification associated with a resource in a cloud computing environment are discussed herein. A system can includes a recommendation engine and a registry to provide centralized management of actions for responding to a notification instead of each service managing actions separately. A machine learned model can generate recommendations for resolving the notification based on a template stored in the registry that associates actions with instructions for presenting the recommendation in a respective interface modality (e.g., Chatbot, mobile application, console, etc.). In some examples, the system can implement a machine learned model, a graph model, and/or a heuristic model, to determine potential actions as recommendation data.

Multi-modal recommendation system in a cloud computing environment

Techniques for a provider network user console with a natural language querying feature. The techniques include collecting a set of templatized query pairs. A pair includes a templatized natural language query (NLQ) and a templatized domain-specific index query language query. The set of templatized query pairs is expanded by substituting named variable tokens in the templatized query pairs with synthetic values to create a set of instantiated query pairs. A pre-trained neural machine translation model is retrained using the set of instantiated query pairs to yield a fine-tuned neural machine translation model. For a natural language query received, the fine-tuned neural machine translation model is used to translate the target natural language query to a corresponding domain-specific index query language query. The domain-specific index query language query is then executed against an index to yield an index result. The techniques reduce or eliminate the need for manual training data generation.

Provider network user console with natural language querying feature

Growing community of inventors

Cupertino, CA, United States of America

Abhijit S Barde