公开(公告)号：US20210157880A1

公开(公告)日：2021-05-27

申请号：US16694364

申请日：2019-11-25

Applicant: Adobe Inc.

Inventor： Gaurav Verma ,  Balaji Vasan Srinivasan ,  Shiv Kumar Saini ,  Niyati Himanshu Chhaya

IPC: G06F17/27 ,  G06F17/24

Abstract: A method for generating stylistic feature prescriptions to align a body of text with one or more target goals includes receiving, at a stylistic feature model, a body of text, where the body of text is selected by a user via a graphical user interface (GUI). The stylistic feature model identifies stylistic features from the body of text and populates a stylistic feature vector with the stylistic features. A trained de-confounded prediction model receives the stylistic feature vector. The trained de-confounded prediction model using the stylistic feature vector generates a prediction value for each of one or more target goals, compares the prediction value for each of the one or more target goals to a target value for each of the one or more target goals and outputs, for display on the GUI, one or more stylistic feature prescriptions to the body of text based on results of the comparing.

公开(公告)号：US20190155880A1

公开(公告)日：2019-05-23

申请号：US15821468

申请日：2017-11-22

Applicant: Adobe Inc.

Inventor： Vishwa Vinay ,  Sopan Khosla ,  Sanket Vaibhav Mehta ,  Sahith Thallapally ,  Gaurav Verma

IPC: G06F17/24

Abstract: Techniques and systems are described in which a document management system is configured to update content of digital documents through use of static and transient tags. A transient tag, for instance, may be associated with portions of the digital document that may be changed and a static tag with portions of the digital document that are not to be changed. An update to the digital document is then triggered by a document management system based on a triggering change made to an initial document portion of the digital document having a transient tag, and is not based on changes made to portions having a static tag or are untagged.

公开(公告)号：US11900056B2

公开(公告)日：2024-02-13

申请号：US18112136

申请日：2023-02-21

Applicant: Adobe Inc.

Inventor： Balaji Vasan Srinivasan ,  Gaurav Verma ,  Bakhtiyar Hussain Syed ,  Anandhavelu Natarajan

IPC: G06F40/253 ,  G06F40/44 ,  G06F40/166 ,  G06N5/022 ,  G06F40/169 ,  G06F40/289 ,  G06V30/418 ,  G06N3/045 ,  G06F18/21 ,  G06N3/088 ,  G06F18/214 ,  G06F40/56

CPC classification number: G06F40/253 ,  G06F40/166 ,  G06F40/44 ,  G06F18/214 ,  G06F18/217 ,  G06F40/169 ,  G06F40/289 ,  G06F40/56 ,  G06N3/045 ,  G06N3/088 ,  G06N5/022 ,  G06V30/418

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

公开(公告)号：US20230196014A1

公开(公告)日：2023-06-22

申请号：US18112136

申请日：2023-02-21

Applicant: Adobe Inc.

Inventor： Balaji Vasan Srinivasan ,  Gaurav Verma ,  Bakhtiyar Hussain Syed ,  Anandhavelu Natarajan

IPC: G06F40/253 ,  G06F40/44 ,  G06F40/166

CPC classification number: G06F40/253 ,  G06F40/44 ,  G06F40/166 ,  G06N5/022

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

公开(公告)号：US11670085B2

公开(公告)日：2023-06-06

申请号：US17090013

申请日：2020-11-05

Applicant: Adobe Inc.

Inventor： Gaurav Verma ,  Balaji Vasan Srinivasan ,  Trikay Nalamada ,  Pranav Goel ,  Keerti Harpavat ,  Aman Mishra

IPC: G06V20/40 ,  G11B27/34 ,  G11B27/034

CPC classification number: G06V20/47 ,  G06V20/41 ,  G06V20/49 ,  G11B27/034 ,  G11B27/34

Abstract: A method for personalized playback of a video as performed by a video platform includes parsing a video into segments based on visual and audio content of the video. The platform creates multimodal fragments that represent underlying segments of the video, and then orders the multimodal fragments based on a preference of a target user. The platform thus enables nonlinear playback of the segmented video in accordance with the multimodal fragments.

公开(公告)号：US11157693B2

公开(公告)日：2021-10-26

申请号：US16800018

申请日：2020-02-25

Applicant: Adobe Inc.

Inventor： Balaji Vasan Srinivasan ,  Gaurav Verma ,  Bakhtiyar Hussain Syed ,  Anandhavelu Natarajan

IPC: G06F40/253 ,  G06F40/44 ,  G06F40/166 ,  G06N5/02 ,  G06F40/169 ,  G06F40/289 ,  G06K9/00 ,  G06F17/00

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

公开(公告)号：US20210279269A1

公开(公告)日：2021-09-09

申请号：US16809222

申请日：2020-03-04

Applicant: Adobe Inc.

Inventor： Gaurav Verma ,  Suryateja B V ,  Samagra Sharma ,  Balaji Vasan Srinivasan

IPC: G06F16/48 ,  G06F40/30 ,  G06F16/435 ,  G06F16/44 ,  G06F16/2457

Abstract: Implementations are described for content fragments aligned to content criteria to enable rich sets of multimodal content to be generated based on specified content criteria, such as content needs pertaining to various content delivery platforms and scenarios. For instance, the described techniques take a set of content (e.g., text, images, etc.) along with a specified content criteria (e.g., business/user need) and creates content fragment variants that are tailored to the content criteria with respect to both the information presented as well as the style of the content presented.

公开(公告)号：US20210193109A1

公开(公告)日：2021-06-24

申请号：US16725716

申请日：2019-12-23

Applicant: Adobe Inc.

Inventor： Gaurav Verma ,  Vishwa Vinay ,  Sneha Chowdary Vinjam ,  Siddharth Sahay ,  Mitansh Jain

IPC: G10L13/04 ,  G06F16/35 ,  G10L13/047 ,  G06F3/0482 ,  G06F3/16 ,  G10L13/08

Abstract: A sound association system identifies one or more aurally active words in digital text. Aurally active words refer to words that denote particular sounds. Context-based sounds corresponding to the one or more aurally active words are also identified. Each context-based sound is anchored to or associated with the corresponding one or more aurally active words and is played back when the digital text is played back or read, providing context-based background sounds associated with the one or more aurally active words. For example, a context-based sound can be played back at a higher volume when the one or more aurally active words are played back or read, and at a lower volume when other words of the digital text are played back or read.