Amazon Technologies, Inc.

Rama Krishna Sandeep Pokkunuri

Akshat Vig

Rajaprabhu Thiruchi Loganathan

Timothy Andrew Rath

Wei Xiao

William Alexander Stevenson

Srivaths Badrinath Copparam

Clarence Wing Yin Ng

Maximiliano Maccanti

Parikshit Shivajirao Pol

Subramanian Sankara Subramanian

Stefano Stefani

Ganesh Kumar Gella

Swapandeep Singh

Roger Scott Jenke

Harshal Pimpalkhute

Kalpesh N Sutaria

Matthew Lee

Yi Zhang

Sudipta Sengupta

Bing Xiang

Gopinath Duddi

Atul Deo

Enrico Sartorello

Yuchen Tian

Meghana Puvvadi

Srinivas Iragavarapu

Safeer Mohiuddin

Kartik Rustagi

Omkar Prakash Kurode

Harini Chandrasekharan

Sudarshan Narasimhan

Swaminathan Sivasubramanian

Ramesh M Nallapati

Yahor Pushkin

Parminder Bhatia

Yaser Al-Onaizan

Andrew Oliver Arnold

Vasanth Philomin

Ankur Deepak Desai

Zijian Wang

Kevin Michael Craft

Praphruetpong Athiwaratkun

Yanitsa Donchev

Lefan Zhang

Gouthamamani Venkatesan

Sri Ranga Akhilesh Bontala

Trevor Andrew Morse

Nikhil Kandoi

Salvatore Romeo

Alexander Johannes Smola

John Baker

Xianglong Huang

Vladimir Zhukov

Vikram Sathyanarayana Anbazhagan

Vivek Bhadauria

Jian Wang

Lokendra Singh Panwar

Rajesh Goli

Marcello Federico

Miguel Ballesteros Martinez

Yong Yuan

Sudhakar Rao Puvvadi

Prashant Mathur

Ameya Karnik

Manikya Pavan Kiran Pothukuchi

Saab Mansour

Georgiana Dinu

Eric J Nowell

Vamshidhar Krishnamurthy Dantu

Jiacheng Guo

Santosh Kumar Ameti

Shang-Wen Daniel Li

Sujan Kumar Gonugondla

Bangrui Liu

Garima Lalwani

Aakash Upadhyay

Jin Hoon Bang

Anna Currey

Wei Fang

Lei Gao

Venkat Rakshith Reddy Swamireddy

Sathish Arumugam Selvaraj

Wasi Uddin Ahmad

Hantian Ding

Ramana Keerthi

Zixuan Lin

Sai Madhu Bhargav Pallem

Haiyang Sun

Ajay Bhaskar Medury

Minaxi Singla

Maximliano Maccanti

Pramod Chandra Samudrala

Himani Amrish Shah

Haifeng Qian

Dan Roth

Xiaokai Wei

Tania Khattar

Navneet Sabbineni

Cheng Ran Li

Code completion suggestions may be proactively obtained and validated. An event that triggers obtaining a code completion suggestion for inclusion in a code file being edited using an integrated development environment may be detected. The code completion suggestion may be obtained. The characters of the code completion suggestion may be compared with characters added to the code file after the detection of the event that triggered obtaining the code completion suggestion to determine whether the code completion suggestion is valid. A valid code completion suggestion may then be displayed.

Validating and providing proactively generated code completion suggestions for code development

Extraction of portions of natural language communications is performed to populate tables. An obtained communication may be associated with one, or more tables. The communication may include natural language data which may extracted and evaluated to predict different value mappings to the table. The value mappings may be confirmed or automatically made to the table.

Extracting data to populate tables from natural language communications

A data set management of a provider network may allow a user to create new data set instances. When a data set instance is created, data set lineage metadata is also generated to describe the new data set instance, including the transformation that was applied to data in order to create the data set instance. When modifications are made to source data (e.g., a data bucket), then the modifications are propagated via transformations to the parent data set instance and to any child data set instances according to the data set lineage metadata in order to update the data set instances. When modifications are made to a parent data set instance to create an updated parent data set instance, then the modifications are propagated via transformations to any child data set instances according to the data set lineage metadata. Transformations and transformation patterns may also be defined and scheduled.

Data set management using data set lineage metadata

Techniques for using a quantized and/or fused model are described. In some examples, a service is to receive a request to use a trained model, the request including input data; apply a trained model to the input data, the application of the trained model includes fusing one or more matrix multiplication operations with element-wise operations; and output a result from the trained model.

Large language models utilizing element-wise operation-fusion

A system for providing code suggestions according to licensing criteria is described. The system comprises computing devices that implement a code suggestion service. The code suggestion service receives a request that specifies licensing criteria via an interface of the code suggestion service. The code suggestion service determines respective licenses for respective source code files according to a source code attribution database from parsing the plurality of source code files that are applicable to the plurality of source code files. The code suggestion service generates a set of candidate code suggestions based, at least in part, on the plurality of source code files. The code suggestion service determines code suggestions from the set of candidate code suggestions that satisfy the licensing criteria based on the respective licenses. The code suggestion service provides the code suggestions determined from the set of candidate source code files that satisfy the licensing criteria.

Software license-based code suggestions

In response to determining that continuous data protection is to be enabled for a particular table of a database service, a service component verifies that automated transmission of change records of the table to a log-structured journal has been configured. A given change record comprises a before-image and an after-image associated with a committed database write, and is assigned a unique sequence number. In response to a determination to restore the table as of a specified point in time, a restore record set is identified from the journal with respect to a selected snapshot of the table. The restore record set includes change records which are not represented in the snapshot and are to be represented in the restored table. A restore result table is created using the selected snapshot and the restore record set.

Scalable log-based continuous data protection for distributed databases

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

Evaluation data sets may be programmatically generated for code generation models. An evaluation data set is obtained that includes items that correspond to different evaluation tests for a code generation system. The individual items of the evaluation data set maybe converted, including the conversion of a function signature for the items, the test statements for the items and using a code generation system to generate the body of the function.

Programmatically generating evaluation data sets for code generation models

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 system that implements a data storage service may store data for a database table in multiple replicated partitions on respective storage nodes. In response to a request to back up a table, the service may back up individual partitions of the table to a remote storage system independently and (in some cases) in parallel, and may update (or create) and store metadata about the table and its partitions on storage nodes of the data storage service and/or in the remote storage system. Backing up each partition may include exporting it from the database in which the table is stored, packaging and compressing the exported partition for upload, and uploading the exported, packaged, and compressed partition to the remote storage system. The remote storage system may be a key-value durable storage system in which each backed-up partition is accessible using its partition identifier as the key.

Backup of partitioned database tables

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

A translation system receives examples of translations between a first language and a second language. In response to receiving request to translate a source text from the first language to the second language, the system ranks the examples based on the example's applicability to one or more portions of the source text. The system performs additional training of a neural network that was pre-trained to translate from the first language to the second language, where the additional training is based on one or more top-ranking examples. The system translates the source text to the second language using the additionally trained neural network.

Machine translation with adapted neural networks

Code search is used to support various features. Code segments may be indexed using a code structure representation of the code segment. Code segments may be compared for similarity to identify a match with an input code segment using a comparison of logic trees generated for the input code segment and a stored code segment in an entry with a matching index value.

Discovering matching code segments according to index and comparative similarity

Information describing changes to a collection of items maintained by a database may be stored in a log file. The information in the log file may be converted into a stream of records describing the changes. The records may be directed to a computing node selected for performing a trigger function in response to the change, based on applying a hash function to a portion of the record, identifying a hash space associated with a value output by the hash function, and mapping from the hash space to the selected computing node.

Distributed stream-based database triggers

Growing community of inventors

Seattle, WA, United States of America

Rama Krishna Sandeep Pokkunuri