Microsoft Technology Licensing, LLC

Ali Sadiq Mohamed

Shunlin Liang

Adam Robert Peck

Prateek Sachdev

Manish Swaminathan

Manas Haribhai Somaiya

Birjodh S Tiwana

Madhulekha Arunmozhi

Vivek Yogesh Tripathi

Parinkumar D Shah

Xin Hu

Shubham Gupta

Strahinja Markovic

Francisco José Claude Faust

Muhammad Hassan Khan

Suruchi H Shah

Siddharth Dangi

Caitlin Marie O'Connor

Nisheedh Raveendran

Zeesha Currimbhoy

Namit Sikka

Vivek Desai

Hari Shankar Sreekumar Menon

Sunny Sanjiv Ketkar

Described herein is a technique to facilitate filtering during candidate retrieval stage performed by an information retrieval system that utilizes embedding models. An aNN indexing structure is created for each end-user, and in some instances, each activity type. This allows a single request for candidate content items to invoke a single process to obtain content items that satisfy the filtering criteria (e.g., in this case, the in-network requirement) from the separate per-end-user indexes.

Embedding-based retrieval techniques for feeds

The disclosed embodiments provide a system for testing machine learning workflows. During operation, the system obtains a configuration for a staging test of a machine learning model, wherein the configuration includes a model name for the machine learning model, a duration of the staging test, and a use case associated with the machine learning model. Next, the system selects a staging test host for the staging test. The system then deploys the staging test on the staging test host in a staging environment, wherein the deployed staging test executes the machine learning model based on live traffic received from a production environment. After the staging test has completed, the system outputs a set of metrics representing a system impact of the machine learning model on the staging test host.

Framework for testing machine learning workflows

Methods, systems, and computer programs are presented for reducing latency for providing a user feed containing one or more posts. One method includes operations for receiving a request to access the user feed and for performing a first query to search posts. The first query uses a first time horizon delimiting a creation time of posts and a first maximum number of posts selected for ranking. The posts from the first query are sent to the client device for presentation on a user interface. Further, a second query is performed to search posts, where the second query uses a second time horizon that is greater than the first time horizon and a second maximum number of posts for ranking that is greater than the first maximum number of posts. The posts from the first query and the second query are merged and sent to the client device for presentation.

Latency optimization for online service feed

The disclosed embodiments provide a system for processing data. During operation, the system stores a conversation containing a series of messages exchanged among a number of participants in a first document containing metadata for the conversation; a second document containing message content for the series of messages, wherein the message content includes a fixed position gap between starting or ending positions in consecutive messages in the series of messages; and one or more additional documents storing message metadata for individual messages in the conversation. Next, the system processes a first search across the series of messages in the conversation using an index of the set of documents. The system also processes, using the index, a second search within individual messages in the series of messages as a span query with a distance that is shorter than the fixed position gap.

Document structures for searching within and across messages

Growing community of inventors

San Jose, CA, United States of America

Ali Sadiq Mohamed