Microsoft Technology Licensing, LLC

Bhaskar Mitra

Tariq Sharif

Lynn Ayres

Mark Rolland Knight

Nicholas Eric Craswell

Yamin Wang

Shobana Balakrishnan

Fernando David Diaz

Matteo Venanzi

Rachel Sirkin

Amy Huyen Phuoc Nguyen

David Anthony Hawking

Robin Thomas

Corbin Louis Rosset

Christophe Jacky Henri Van Gysel

Emine Yilmaz

Grzegorz Stanislaw Kukla

Nicola Cancedda

Roy Rosemarin

Sri Ramya Mallipudi

Described herein is a mechanism for utilizing a neural network to identify and rank search results. A machine learning model is trained by converting training data comprising query-document entries into query term-document entries. The query term-document entries are utilized to train the machine learning model. A set of query terms are identified. The query terms can be derived from a query history. The trained machine learning model is used to calculate document ranking scores for the query terms and the resultant scores are stored in a pre-calculated term-document index. A query to search the document index is broken down into its constituent terms and an aggregate document ranking score is calculated from a weighted sum of the document ranking scores corresponding to the individual query terms. Because the term-document index can be pre-calculated, it can be downloaded to provide deep learning search capabilities in a computationally limited environment.

Neural network for search retrieval and ranking

Systems and methods are provided that automatically process a message input, construct an intelligent query based on the processing of the message input, and provide at least one attachable entity according to the processing results and the intelligent query. In some example aspects, a message is received. A natural language processor to determine if the message is requesting content may then process the message. If the message is determined to be requesting content, then candidate sub-queries may be generated to serve as a training set for a query that will be sent to an external search engine to retrieve the attachable entity. The sub-queries may be ranked in order of relevance and performance score. The highest ranked sub-queries may then be used in the actual query that is fired against the external search engine. The external search engine may search local and remote repositories for the top K most relevant attachable entities and present them to a user for attachment in a reply message.

Intelligent query system for attachments

Growing community of inventors

London, United Kingdom

Bhaskar Mitra