-
公开(公告)号：US20190197184A1
公开(公告)日：2019-06-27
申请号：US15854320
申请日：2017-12-26
Applicant: ADOBE INC.
Inventor： Balaji Vasan Srinivasan , Pranav Ravindra Maneriker , Natwar Modani , Kundan Krishna
CPC classification number: G06F16/334 , G06F16/338 , G06F17/2705 , G06F17/277
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating corpus-based content generation, in particular, using graph-based multi-sentence compression to generate a final content output. In one embodiment, pre-existing source content is identified and retrieved from a corpus. The source content is then parsed into sentence tokens, mapped and weighted. The sentence tokens are further parsed into word tokens and weighted. The mapped word tokens are then compressed into candidate sentences to be used in a final content. The final content is assembled using ranked candidate sentences, such that the final content is organized to reduce information redundancy and optimize content cohesion.
-
22.发明申请公开(公告)号：US20190155877A1
公开(公告)日：2019-05-23
申请号：US15816976
申请日：2017-11-17
Applicant: Adobe Inc.
Inventor： Saumitra Sharma , Kundan Krishna , Balaji Vasan Srinivasan , Aniket Murhekar
CPC classification number: G06F17/2264 , G06F16/345 , G06F17/274 , G06F17/2785 , G06F17/2795 , G06F17/2854 , G06N3/0445 , G06N3/0454 , G06N3/08 , G06N20/00
Abstract: A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using a linguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, to learn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary.
-
公开(公告)号：US11748501B2
公开(公告)日：2023-09-05
申请号：US16984866
申请日：2020-08-04
Applicant: Adobe Inc.
Inventor： Tanya Goyal , Sanket Vaibhav Mehta , Balaji Vasan Srinivasan , Ankur Jain
CPC classification number: G06F21/6209 , G06F21/62 , G06F21/6218 , G06F16/35 , G06F16/355
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitate identification of security policies for documents. In one embodiment, content features are identified from a set of documents having assigned security policies. The content features and corresponding security policies are analyzed to generate a security policy prediction model. Such a security policy prediction model can then be used to identify a security policy relevant to a document.
-
24.发明授权公开(公告)号：US11714972B2
公开(公告)日：2023-08-01
申请号：US17529886
申请日：2021-11-18
Applicant: ADOBE INC.
Inventor： Balaji Vasan Srinivasan , Anandhavelu Natarajan , Abhilasha Sancheti
Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for facilitating stylistic expression transfers in machine translation of source sequence data. Using integrated loss functions for style transfer along with content preservation and/or cross entropy, source sequence data is processed by an autoencoder trained to reduce loss values across the loss functions at each time step encoded for the source sequence data. The target sequence data generated by the autoencoder therefore exhibits reduced loss values for the integrated loss functions at each time step, thereby improving content preservation and providing for stylistic expression transfer.
-
公开(公告)号：US20230114742A1
公开(公告)日：2023-04-13
申请号：US17450250
申请日：2021-10-07
Applicant: Adobe Inc.
Inventor： Vinay Aggarwal , Vishwa Vinay , Rizurekh Saha , Prabhat Mahapatra , Niyati Himanshu Chhaya , Harshit Agrawal , Chloe McConnell , Bhanu Prakash Reddy Guda , Balaji Vasan Srinivasan
IPC: G06F40/186 , G06F40/109 , G06N20/00 , G06F40/30 , G06K9/62
Abstract: Techniques for template generation from image content includes extracting information associated with an input image. The information comprises: 1) layout information indicating positions of content corresponding to a content type of a plurality of content types within the input image; and 2) text attributes indicating at least a font of text included in the input image. A user-editable template having the characteristics of the input image is generated based on the layout information and the text attributes
-
Patent Agency Ranking
公开(公告)号：US20220343189A1
公开(公告)日：2022-10-27
申请号：US17237892
申请日：2021-04-22
Applicant: Adobe Inc.
Inventor： Niyati Himanshu Chhaya , Niranjan Kumbi , Balaji Vasan Srinivasan , Akangsha Bedmutha , Ajay Awatramani , Sreekanth Reddy
Abstract: Certain embodiments involve using machine-learning methods to generate a recommendation for sequential content items. A method involves accessing a content item associated with an interaction stage in an online environment. A stage graph, which includes a ratio of interactions, of the content item is generated. An additional content item that includes additional stage-transition content is identified. A sequencing function outcome indicating a portion of the ratio of interactions is determined. A transition probability of receiving an interaction with stage-transition content and an additional interaction with the additional stage-transition content is calculated. A content provider system is caused to provide a recipient device with interactive content that includes the additional content item.
-
公开(公告)号：US20220147713A1
公开(公告)日：2022-05-12
申请号：US17092230
申请日：2020-11-07
Applicant: Adobe Inc.
Inventor： Aparna Garimella , Kiran Kumar Rathlavath , Balaji Vasan Srinivasan , Anandhavelu Natarajan , Akhash Nakkonda Amarnath , Akash Pramod Yalla
IPC: G06F40/284 , G06F40/56 , G06K9/62
Abstract: A system for generating text using a trained language model comprises an encoder that includes a debiased language model that penalizes generated text based on an equalization loss that quantifies first and second probabilities of respective first and second tokens occurring at a first point in the generated text. The first and second tokens define respective first and second groups of people. The system further comprises a decoder configured to generate text using the debiased language model. The decoder is further configured to penalize the generated text based on a bias penalization loss that quantifies respective probabilities of the first and second tokens co-occurring with a generated word. The encoder and decoder are trained to produce the generated text using a task-specific training corpus.
-
28.发明授权公开(公告)号：US11210477B2
公开(公告)日：2021-12-28
申请号：US16407704
申请日：2019-05-09
Applicant: ADOBE INC.
Inventor： Balaji Vasan Srinivasan , Anandhavelu Natarajan , Abhilasha Sancheti
Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for facilitating stylistic expression transfers in machine translation of source sequence data. Using integrated loss functions for style transfer along with content preservation and/or cross entropy, source sequence data is processed by an autoencoder trained to reduce loss values across the loss functions at each time step encoded for the source sequence data. The target sequence data generated by the autoencoder therefore exhibits reduced loss values for the integrated loss functions at each time step, thereby improving content preservation and providing for stylistic expression transfer.
-
公开(公告)号：US20210264109A1
公开(公告)日：2021-08-26
申请号：US16800018
申请日：2020-02-25
Applicant: Adobe Inc.
IPC: G06F40/253 , G06F40/166 , G06F40/44
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.
-
30.发明授权公开(公告)号：US11062087B2
公开(公告)日：2021-07-13
申请号：US16262655
申请日：2019-01-30
Applicant: Adobe Inc.
Inventor： Balaji Vasan Srinivasan , Kushal Chawla , Mithlesh Kumar , Hrituraj Singh , Arijit Pramanik
IPC: G06F40/284 , G06N20/00
Abstract: Certain embodiments involve tuning summaries of input text to a target characteristic using a word generation model. For example, a method for generating a tuned summary using a word generation model includes generating a learned subspace representation of input text and a target characteristic token associated with the input text by applying an encoder to the input text and the target characteristic token. The method also includes generating, by a decoder, each word of a tuned summary of the input text from the learned subspace representation and from a feedback about preceding words of the tuned summary. The tuned summary is tuned to target characteristics represented by the target characteristic token.
-
-
-
-
-
-
-
-
-
Search Results
75
records
(took 0.025 seconds)
