Microsoft Technology Licensing, LLC

Qi Liu

Thomas Moscibroda

Qifa Ke

Arash Ghanaie-Sichanie

Frank Torsten Bernd Seide

Xiang Yu

Jian Wu

Sanjay Sureshchandra Dubey

Srinivas Vadrevu

Senthil Kumar Velayutham

Nicholas David Burton

Yang Chen

Gang Luo

Hardik Bati

Lihong Pei

Yawen Wei

Edward Wu

Oana Nicolov

Rajanala Sai Krishna Sravanthi

Krishna Sravanthi Rajanala Sai

Dario Bigongiari

Waitat Peter Poon

Ying Yan

A system and method for selecting a target device out of a larger group of candidate devices for rendering a response from a virtual assistant to an end-user is disclosed. The system determines that a same trigger phrase included in an utterance has been received by multiple devices that are in proximity to one another at around the same time. These candidate devices can collect attention data, such as user gaze toward a device, to select the device that was most likely the intended recipient of the utterance. The system is configured to control the virtual assistant to render a response solely via the selected device.

Selective response rendering for virtual assistants

Examples of the present disclosure describe systems and methods relating to generating relevance scores for one or more words of a passage which is an answer to a natural language query. For instance, a passage extracted from a highly relevant electronic file along with the query may encoded and augmented to generate a multi-dimensional, augmented semantic vectors using recurring neural networks. The augmented semantic vectors along with a multi-dimensional vector that represent words of the passage may be decoded to generate relevance scores for one or more words of the passage, based on levels of relevance to the query.

Method and system for highlighting answer phrases

Generally discussed herein are methods, systems, and apparatuses for tracking user interaction with sponsored and/or unsponsored content. A method can include receiving a tracking event packet including data fields comprising a packet identification, a tracking event identifier, a content identifier, a cost, a campaign identifier, and/or an advertiser identifier, determining whether the tracking event packet is a duplicate based on the packet identification, aggregating non-duplicate tracking event packets by advertiser identification such that packets with advertiser identifications that hash to a same value are aggregated together, and transferring aggregated tracking event packets to a first database and a second database, the first database includes data stored for analytics and the second database includes data stored for billing and campaign performance monitoring.

Tracking interaction with sponsored and unsponsored content

A summary of a document is generated in near real time. In aspects, an indication to summarize the document is received and the document is processed to generate a summary. For instance, processing includes extracting sentences from the document and generating a plurality of candidate passages from the extracted sentences. Features are extracted from each of the plurality of candidate passages and each candidate passage is ranked based at least in part on the extracted features. High-ranking candidate passages are considered likely to be important and/or representative of the document. A summary of the document is generated including one or more of the high-ranking candidate passages. The summary includes portions of the document that are considered important and/or representative of the document, so a user may review the summary in lieu of reading the entire document.

Automatic document summarization using search engine intelligence

Growing community of inventors

Santa Clara, CA, United States of America

Qi Liu