公开(公告)号：US11604924B2

公开(公告)日：2023-03-14

申请号：US17148125

申请日：2021-01-13

Applicant: Adobe, Inc.

Inventor： Shagun Kush ,  Sachin Soni ,  Nikita Kapoor ,  Carl Iwan Dockhorn ,  Ashish Rawat ,  Ajay Jain ,  Abhishek Jain

IPC: G06F40/106 ,  G06F40/289 ,  G06F40/30

Abstract: Techniques are provided herein for generating improved document summaries that consider the amount of time that has passed since the user last accessed the document. The length of time that has passed since the user has accessed each previous portion of the document is used as a variable to determine how much the summary should focus on each of the previously read sections of the document. When a document is accessed by a user, a relevance score is assigned to content from previously accessed sections of that document, where the relevance score is weighted based on how long ago each of the sections was accessed by the user. Once the various content items of previous sections have been provided relevance scores, selected sentences with the highest relevance scores are fed to a deep learning sequence-to-sequence model is used to build the document summary.

公开(公告)号：US20220222439A1

公开(公告)日：2022-07-14

申请号：US17148125

申请日：2021-01-13

Applicant: Adobe, Inc.

Inventor： Shagun Kush ,  Sachin Soni ,  Nikita Kapoor ,  Carl Iwan Dockhorn ,  Ashish Rawat ,  Ajay Jain ,  Abhishek Jain

IPC: G06F40/289

Abstract: Techniques are provided herein for generating improved document summaries that consider the amount of time that has passed since the user last accessed the document. The length of time that has passed since the user has accessed each previous portion of the document is used as a variable to determine how much the summary should focus on each of the previously read sections of the document. When a document is accessed by a user, a relevance score is assigned to content from previously accessed sections of that document, where the relevance score is weighted based on how long ago each of the sections was accessed by the user. Once the various content items of previous sections have been provided relevance scores, selected sentences with the highest relevance scores are fed to a deep learning sequence-to-sequence model is used to build the document summary.

公开(公告)号：US11450310B2

公开(公告)日：2022-09-20

申请号：US16989012

申请日：2020-08-10

Applicant: ADOBE INC.

Inventor： Nikita Kapoor ,  Jaya Dodeja ,  Nikaash Puri

IPC: G10L15/06 ,  G10L19/04 ,  G10L15/02 ,  G10L15/18 ,  G10L15/16 ,  G10L25/51

Abstract: Systems and methods for spoken language understanding are described. Embodiments of the systems and methods receive audio data for a spoken language expression, encode the audio data using a multi-stage encoder comprising a basic encoder and a sequential encoder, wherein the basic encoder is trained to generate character features during a first training phase and the sequential encoder is trained to generate token features during a second training phase, and decode the token features to generate semantic information representing the spoken language expression.