-
公开(公告)号：US20160350724A1
公开(公告)日：2016-12-01
申请号：US15231437
申请日：2016-08-08
Applicant: Microsoft Technology Licensing, LLC
Inventor： John C. Tang , Aaron Hoff , Kori Inkpen Quinn , Paul Johns , Asta Roseway , Chen Zhao , Xiang Cao , Jennifer Marlow
CPC classification number: G06Q10/1095 , G06F17/30 , G06F17/30056 , G06F17/30058 , G06F17/30598 , H04L65/403 , H04L67/28
Abstract: Embodiments described herein relate to enabling a lightweight way of recording and sharing video messages intended to provide input to a future meeting that cannot be personally attended. A person who cannot attend the meeting pre-records their thoughts and remarks for the meeting as video clips for presentation at the meeting. A physical device with at least a display is presented at the meeting. The physically present participants can play the pre-recorded clips on the device. Video of participants' responses to the clips is recorded and made available so that the represented attendee can view the participants' responses.
-
公开(公告)号：US20240338414A1
公开(公告)日：2024-10-10
申请号：US18661397
申请日：2024-05-10
Applicant: Microsoft Technology Licensing, LLC
Inventor： Chenyan Xiong , Chen Zhao , Corbin Louis Rosset , Paul Nathan Bennett , Xia Song , Saurabh Kumar Tiwary
IPC: G06F16/93 , G06F16/903 , G06N3/04 , G06N3/08
CPC classification number: G06F16/93 , G06F16/90335 , G06N3/04 , G06N3/08
Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.
-
公开(公告)号：US10163077B2
公开(公告)日：2018-12-25
申请号：US15231437
申请日：2016-08-08
Applicant: Microsoft Technology Licensing, LLC
Inventor： John C. Tang , Aaron Hoff , Kori Inkpen , Paul Johns , Asta Roseway , Chen Zhao , Xiang Cao , Jennifer Marlow
Abstract: Embodiments described herein relate to enabling a lightweight way of recording and sharing video messages intended to provide input to a future meeting that cannot be personally attended. A person who cannot attend the meeting pre-records their thoughts and remarks for the meeting as video clips for presentation at the meeting. A physical device with at least a display is presented at the meeting. The physically present participants can play the pre-recorded clips on the device. Video of participants' responses to the clips is recorded and made available so that the represented attendee can view the participants' responses.
-
公开(公告)号：US20220374479A1
公开(公告)日：2022-11-24
申请号：US17866854
申请日：2022-07-18
Applicant: Microsoft Technology Licensing, LLC
Inventor： Chenyan Xiong , Chen Zhao , Corbin Louis Rosset , Paul Nathan Bennett , Xia Song , Saurabh Kumar Tiwary
IPC: G06F16/93 , G06F16/903 , G06N3/04 , G06N3/08
Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.
-
公开(公告)号：US11423093B2
公开(公告)日：2022-08-23
申请号：US16582582
申请日：2019-09-25
Applicant: Microsoft Technology Licensing, LLC
Inventor： Chenyan Xiong , Chen Zhao , Corbin Louis Rosset , Paul Nathan Bennett , Xia Song , Saurabh Kumar Tiwary
IPC: G06F16/93 , G06F16/903 , G06N3/04 , G06N3/08
Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.
-
Patent Agency Ranking
公开(公告)号：US10242821B2
公开(公告)日：2019-03-26
申请号：US15269818
申请日：2016-09-19
Applicant: Microsoft Technology Licensing, LLC
Inventor： Hong Z. Tan , Zhaoyuan Ma , Chen Zhao
Abstract: Disclosed herein are techniques and systems for providing simulated, haptic feedback that is local to physical, non-actuating keys of a keyboard. A keyboard includes a plurality of non-actuating keys defined in a cover portion of the keyboard, a plurality of force-producing mechanisms coupled to a substrate underneath and adjacent the cover portion. The force-producing mechanisms may be positioned on suspended portions of the substrate that are mechanically isolated and arranged on the substrate to substantially correspond to a layout of the plurality of non-actuating keys. The force-producing mechanisms may be individually actuated to deflect the suspended portions of the substrate underneath the cover portion to create a tactile sensation for a user's finger that is local to a particular key. In some embodiments, the force-producing mechanisms are piezoelectric actuators.
-
公开(公告)号：US12013902B2
公开(公告)日：2024-06-18
申请号：US17866854
申请日：2022-07-18
Applicant: Microsoft Technology Licensing, LLC
Inventor： Chenyan Xiong , Chen Zhao , Corbin Louis Rosset , Paul Nathan Bennett , Xia Song , Saurabh Kumar Tiwary
IPC: G06F16/93 , G06F16/903 , G06N3/04 , G06N3/08
CPC classification number: G06F16/93 , G06F16/90335 , G06N3/04 , G06N3/08
Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.
-
公开(公告)号：US11586838B2
公开(公告)日：2023-02-21
申请号：US16460271
申请日：2019-07-02
Applicant: Microsoft Technology Licensing, LLC
Abstract: Systems and techniques for end-to-end fuzzy entity matching are described herein. A first input and a second input may be received. The first input and the second input may be evaluated to identify common attribute types. A set of attribute entity matching models may be selected that correspond to the attribute types. The first input and the second input may be evaluated using the set of attribute entity matching models to determine a set of weighted scores for attribute pairs in the first input and the second input. The set of weighted scores may be evaluated using a table-level entity matching model to identify a common entity included in the first input and the second input. A linking dataset may be generated that includes a cross-linking facility indicating a relationship between a first entity descriptor in the first input and a second entity descriptor in the second input.
-
公开(公告)号：US20210089594A1
公开(公告)日：2021-03-25
申请号：US16582582
申请日：2019-09-25
Applicant: Microsoft Technology Licensing, LLC
Inventor： Chenyan Xiong , Chen Zhao , Corbin Louis Rosset , Paul Nathan Bennett , Xia Song , Saurabh Kumar Tiwary
IPC: G06F16/93 , G06F16/903 , G06N3/04 , G06N3/08
Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.
-
公开(公告)号：US20200272845A1
公开(公告)日：2020-08-27
申请号：US16460271
申请日：2019-07-02
Applicant: Microsoft Technology Licensing, LLC
Abstract: Systems and techniques for end-to-end fuzzy entity matching are described herein. A first input and a second input may be received. The first input and the second input may be evaluated to identify common attribute types. A set of attribute entity matching models may be selected that correspond to the attribute types. The first input and the second input may be evaluated using the set of attribute entity matching models to determine a set of weighted scores for attribute pairs in the first input and the second input. The set of weighted scores may be evaluated using a table-level entity matching model to identify a common entity included in the first input and the second input. A linking dataset may be generated that includes a cross-linking facility indicating a relationship between a first entity descriptor in the first input and a second entity descriptor in the second input.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.016 seconds)
