Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Sudipta Sengupta

Jin Li

Bing Xiang

Ramesh M Nallapati

Zhiguo Wang

David Bruce Lomet

Biplob Kumar Debnath

Paul Adrian Oltean

Poorna Chand Srinivas Perumalla

Justin Jon Levandoski

Patrick Ng

Swaminathan Sivasubramanian

Nafea Bshara

Leo Parker Dirac

Andrea Olgiati

Matthew James Wood

Stephen Michael Ash

Minghua Chen

Dominic Rajeev Divakaruni

Bratin Saha

Sharanabasappa Parashuram Revadigar

Stefano Stefani

Philip Andrew Chou

Albert Gordon Greenberg

Sanjeev Mehrotra

Parveen Kumar Patel

Ran Kalach

David A Maltz

Timothy Jones

Parantap Lahiri

Ronakkumar N Desai

Srinivas Iragavarapu

Jun Wang

Hanbo Li

Parminder Bhatia

Atul Deo

Andrew Oliver Arnold

Yuchen Tian

Matthew Lee

Yung Haw Wang

Gregory David Adams

Miroslav Ponec

Praphruetpong Athiwaratkun

Ankur Deepak Desai

Peng Xu

Ron Diamant

Ranveer Chandra

Randy Renfu Huang

Saileshwar Krishnamurthy

Rama Krishna Sandeep Pokkunuri

Kamal Kant Gupta

Mukul Vijay Karnik

Yongsik Yoon

Vignesh Vivekraja

James Robert Benton

Tong L Wynn

Douglas Scott Cerny

Jaeyun Noh

Nanyan Li

Rishav Chakravarti

Stephanie Weeks

Sangil Song

Jiarong Jiang

Yanitsa Donchev

Zijian Wang

Xiaofei Ma

Ramarathnam R Venkatesan

Wei Xiao

Matthew Shawn Wilson

Abhishek Gupta

Navendu Jain

Wolfram Schulte

Rahul Sharma

Cheng Huang

Roy Peter D'Souza

David Robert Thomas

Shao Liu

Alexander Johannes Smola

Omkant Pandey

Pejus Manoj Das

Cicero Nogueira Dos Santos

Changhoon Kim

Lars Kuhtz

Ahmed El-Shimi

Chenguang Zhu

Chun Ho Cheung

Sumeetkumar Veniklal Maru

Jae Young Do

Saurabh Kumar Singh

Dimitrios Soulios

Haifeng He

John Thomas Erickson

Sayandeep Sen

Jalaja C Kurubarahalli

Yong Yuan

Henghui Zhu

James Laurence Finnerty

Vinod Sridharan

Manish Jain

Julio Delgado Mangas

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

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 schema and cell value aware Named Entity Recognition (NER) model is used to perform natural language queries. Natural language queries may be received via an interface of a natural language query processing system. A fuzzy search may be performed that allows non-exact matches for column names or cell values of data sets potentially used to answer the natural language query. An NER model that adds a type embedding for an exact match of a column name or cell found in the fuzzy search that corresponds to a span of one or more words may be applied as part of generating the entity prediction for the natural language query. One or more queries to at least one of the data sets may be performed to return a result to the natural language query using the entity prediction generated by the NER machine learning model.

Schema and cell value aware named entity recognition model for executing natural language queries

Techniques for handling natural language query processing are described. In some examples, a sequence-to-sequence model is used to handle a natural language query. Post-processing of a result of the sequence-to-sequence model utilizes fine-grained information from an entity linker. In some examples, the sequence-to-sequence model and aspects of a natural language query pipeline are used to handle a natural language query.

Natural language query processing

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

Methods and systems for training a neural network are provided. In one example, an apparatus comprises a memory that stores instructions; and a hardware processor configured to execute the instructions to: control a neural network processor to perform a loss gradient operation to generate data gradients; after the loss gradient operation completes, control the neural network processor to perform a forward propagation operation to generate intermediate outputs; control the neural network processor to perform a backward propagation operation based on the data gradients and the intermediate outputs to generate weight gradients; receive the weight gradients from the neural network processor; and update weights of a neural network based on the weight gradients.

Neural network training under memory restraint

Pre-fix matching may constrain the generation of next token predictions. Input text to perform a next token prediction may be received. Multiple tokens may be determined from the input text, including a partial token. From possible tokens, one or more matching possible tokens with the partial token may be identified. Next token predictions may then be filtered using the identified possible tokens in order to ensure that the partial token is matched.

Constrained prefix matching for generating next token predictions

Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

Interactive assistance for executing natural language queries to data sets

Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes attaching a first set of one or more accelerator slots of an accelerator appliance to an application instance of a multi-tenant provider network according to an application instance configuration, the application instance configuration to define per accelerator slot capabilities to be used by an application of the application instance, wherein the multi-tenant provider network comprises a plurality of computing devices configured to implement a plurality of virtual compute instances, and wherein the first set of one or more accelerator slots is implemented using physical accelerator resources accessible to the application instance; while performing inference using the loaded machine learning model of the application using the first set of one or more accelerator slots on the attached accelerator appliance, managing resources of the accelerator appliance using an accelerator appliance manager of the accelerator appliance.

Fault-tolerant accelerator based inference service

Techniques for batch mode execution for calls to remote services are described. A method of batch mode execution for calls to remote services may include generating, by a query service of a provider network, a query plan to optimize a query for batch processing of data, the query plan including at least a function reference to a function provided by at least one service of the provider network, executing the query plan to invoke the function associated with the function reference, wherein a batch function generates a request including a batch of service calls to be processed by the at least one service, sends the request including the batch of service calls to the at least one service, and obtains a plurality of machine learning responses from the at least one service, and generating a query response based on the plurality of responses.

Use of batch mode function execution in database engines to enable efficient calls to remote services

Techniques for making machine learning inference calls for database query processing are described. In some embodiments, a method of making machine learning inference calls for database query processing may include generating a first batch of machine learning requests based at least on a query to be performed on data stored in a database service, wherein the query identifies a machine learning service, sending the first batch of machine learning requests to an input buffer of an asynchronous request handler, the asynchronous request handler to generate a second batch of machine learning requests based on the first batch of machine learning requests, and obtaining a plurality of machine learning responses from an output buffer of the asynchronous request handler, the machine learning responses generated by the machine learning service using a machine learning model in response to receiving the second batch of machine learning requests.

Machine learning inference calls for database query processing

Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

Multiple stage filtering for natural language query processing pipelines

Query restatements may be provided for explaining natural language query results. A natural language query is received at a natural language query processing system. An intermediate representation of the natural language query is generated for executing the natural language query. The intermediate representation is translated into a natural language restatement of the natural language query. The natural language restatement is provided with a result of the natural language query via an interface of the natural language query processing system.

Providing query restatements for explaining natural language query results

Growing community of inventors

Redmond, WA, United States of America

Sudipta Sengupta