Microsoft Technology Licensing, LLC

Marc Manuel Johannes Brockschmidt

Miltiadis Allamanis

Alexander Lloyd Gaunt

Christian Canton

Johnny S Campbell

Sebastian Nowozin

Joseph John McDaid

Daniel Stefan Tarlow

Matej Balog

Andrew William Stegmaier

Vikas Yadav

Sjoerd Roelof De Jong

Robert David Ohn Tinn

Juliana Patricia Vicente Franco

Sneha Khullar

Benjamin Zorn

Mark Alistair Wilson-Thomas

Simon Calvert

Rishabh Singh

Sylvan Wesley Clebsch

Kesavan Shanmugam

Pallavi Choudhury

Matthew John Parkinson

Oleksandr Polozov

John Sells Tilford

Deborah Chen

Srivatsn Narayanan

Guillermo Serrato Castilla

Saswat Padhi

Syed Samin Ishtiaq

Jade Ella Carla Alglave

Pengcheng Yin

Andrew Madison Kent

Joshua Bates Stevens

Systems, methods, and computer-readable storage devices are disclosed for improved table identification in a spreadsheet. One method including: receiving a spreadsheet including at least one table; identifying, using machine learning, one or more classes of a plurality of classes for each cell of the received spreadsheet, wherein the plurality of classes include corners and not-a-corner; and inducing at least one table in the received spreadsheet based on the one or more identified classes for each cell of the received spreadsheet.

Systems, methods, and computer-readable media for improved table identification using a neural network

A computer program predictor is described which has a processor configured to access a program attribute predictor; and a memory storing a search component configured to search a space of possible programs, to find a program which, given an input data instance and an output data instance, will compute the output data instance from the input data instance, the search being guided by attributes predicted by the attribute predictor given the input data instance and the output data instance.

Program predictor

Systems, methods, and software are disclosed herein for enhancing functions and formulas in spreadsheets. A computing apparatus detects a beginning of a formula in a cell of a spreadsheet. In response to detecting the beginning of the formula, the computing apparatus identifies one or more vector representations of a context of the cell and supplies the one or more vector representations as input to one or more machine learning models. The one or more machine learning models produce output comprising one or more suggested functions for the formula and one or more suggested operands, which the computing apparatus presents in a user interface to the spreadsheet.

Suggested functions for formulas in spreadsheets

An editing tool is described which has a memory storing a neural network having been trained to compute a change representation from pairs, each pair comprising a representation of a first version of a content item and a second version of the content item, and for each of the change representations, predict an updated content item from the change representation and the first version of the content item. The editing tool has a processor configured to receive an input content item and to compute an updated version of the input content item according to a change representation, using the neural network.

Automated content editor

Systems, methods, and software are disclosed herein for enhancing functions and formulas in spreadsheets. A computing apparatus detects a beginning of a formula in a cell of a spreadsheet. In response to detecting the beginning of the formula, the computing apparatus identifies a vector representation of a context of the cell and supplies the vector representation as input to one or more machine learning models. The one or more machine learning models produce output comprising one or more suggested functions for the formula and one or more suggested operands, which the computing apparatus presents in a user interface to the spreadsheet.

Form-based formula editing in spreadsheets

In various examples, there is a computer-implemented method for providing packages for processing on a computer system. The method creates a secure connection to an enclave and retrieves a quote to verify that the enclave is genuine and that it contains a predetermined process. The predetermined process is configured to create an enclave for itself and determine that an initial state of the computer system is equivalent to a predetermined state based on a quote retrieved from a security module. The predetermined process is further configured to receive a package to be processed by the computer system and cause the processor to process the package outside of the enclave. In response to verifying the enclave, the method provides a package to be processed by the computer system.

Package processing

Improving how a codebase, which may include source code, related databases, test files, code history, and/or changes, is drafted, edited, debugged, or otherwise developed. Machine learning is performed on a model codebase to establish a machine learning model. When a change to a codebase occurs, the machine learning model may be applied to evaluate that change. A change context providing context for this change is accessed. An analyzer then analyzes the change using the machine learning model and at least a part of the change context to generate an analysis result. Some information about the result is rendered. After rendering that information, a determination regarding how a user responded to the information is performed, and a subsequent analysis is then modified based on the user's response.

Code development using continued machine learnings

Improving how a codebase is developed by analyzing the variables in the codebase's source code. Learned characteristics of a codebase are derived by obtaining context for some of the source code's variables. This context represents semantics and/or patterns associated with those variables. Once the learned characteristics are derived, they are then modified, or rather tuned, by incorporating context from second source code. Particular context for a particular variable used within the second source code is then obtained. This particular context represents semantics and/or patterns associated with the particular variable. This particular context is then analyzed using the learned characteristics to generate zero, one or more anticipated variables. Later, a notification regarding these anticipated variables is displayed. In some situations, conducting the analysis is a part of a variable renaming analysis while in other situation the analysis is a part of a variable misuse analysis.

Variable analysis using code context

Growing community of inventors

Cambridge, United Kingdom

Marc Manuel Johannes Brockschmidt