Microsoft Technology Licensing, LLC

Neil Toronto

Andrew Donald Gordon

Advait Sarkar

Benjamin Zorn

Carina Suzana Negreanu

Brian Paul Slininger

Sruti Srinivasa Ragavan

Benjamin Edward Rampson

Christian Canton

Johnny S Campbell

Vu Minh Le

Elnaz Nouri

Simon Peyton Jones

Richard Matthew McCutchen

Shraddha Govind Barke

Christian Leopold Bejamin Poelitz

Anusha Iyer

The indirect querying of models to determine capabilities possessed by the model. Such indirect queries take the form of model input that potentially includes a natural language input user data. Such model input is structured such that the output of the model is either not natural language at all, or else is natural language that is not semantically responsive to the natural language input. Nevertheless, the output is evaluated to estimate or determine the capability possessed by the model. Thus, models may be more fully utilized to their better potential.

Model capability extraction

The generation of a response to a task prompt that represents a task to perform on declarative code. The response is generated with the aid of a language model that was trained on imperative code. The declarative code includes declarations about data. A task prompt represents a task to perform on the declarative code. At least a portion of the declarative code and at least a portion of the task prompt are converted into input imperative code. The input imperative code is then caused to be provided as input to the language model, resulting in the language model generating output imperative code. At least a portion of the output imperative code is then converted into a response to the task prompt.

Responding to task prompt on declarative code using language model

To prevent spreadsheet errors, a solution is disclosed that provides a multiple-region spreadsheet including additional representations, providing readily usable creation and editing of computational structure operations, without altering the conventional grid representation of a spreadsheet or its formula syntax. The multiple-region spreadsheet may include a traditional row-column arrangement of cells in a grid format, along with a calculation view pane intended to display underlying formulas used in the grid along with truncated cell assignments.

Spreadsheet cell calculation view providing multiple-representation editing

Technology is disclosed herein for handing approximate (or uncertain) values in spreadsheet applications. More specifically, the technology describes spreadsheet applications that support arrays or sets of approximate (or uncertain) values as native entities. An approximate (or uncertain) value may be the value of a cell of the spreadsheet that is resolvable by formula, charts and other functionalities. In some implementations, approximate values may include a range of data and a probability distribution that can be automatically created by the spreadsheet application, generated based on context, input by the user, etc. Because the approximate (or uncertain) value is natively available, it can be incorporated in a spreadsheet like other values. Additionally, the approximate (or uncertain) values can automatically propagate through a spreadsheet calculation to obtain a final approximate result. The techniques also describe various ways to represent uncertain values in cells and to visualize the probability distribution.

Natively handling approximate values in spreadsheet applications

Growing community of inventors

Cambridge, United Kingdom

Neil Toronto