公开(公告)号：US12045272B2

公开(公告)日：2024-07-23

申请号：US17370899

申请日：2021-07-08

Applicant: ADOBE INC.

Inventor： Saurabh Mahapatra ,  Niyati Chhaya ,  Snehal Raj ,  Sharmila Reddy Nangi ,  Sapthotharan Nair ,  Sagnik Mukherjee ,  Jay Mundra ,  Fan Du ,  Atharv Tyagi ,  Aparna Garimella

IPC: G06F16/34 ,  G06F16/332 ,  G06F40/30 ,  G06N3/04 ,  G06N3/044 ,  G06N3/08

CPC classification number: G06F16/345 ,  G06F16/3329 ,  G06F40/30 ,  G06N3/04 ,  G06N3/044 ,  G06N3/08

Abstract: A text summarization system auto-generates text summarization models using a combination of neural architecture search and knowledge distillation. Given an input dataset for generating/training a text summarization model, neural architecture search is used to sample a search space to select a network architecture for the text summarization model. Knowledge distillation includes fine-tuning a language model for a given text summarization task using the input dataset, and using the fine-tuned language model as a teacher model to inform the selection of the network architecture and the training of the text summarization model. Once a text summarization model has been generated, the text summarization model can be used to generate summaries for given text.

公开(公告)号：US20230020886A1

公开(公告)日：2023-01-19

申请号：US17370899

申请日：2021-07-08

Applicant: ADOBE INC.

Inventor： Saurabh Mahapatra ,  Niyati Chhaya ,  Snehal Raj ,  Sharmila Reddy Nangi ,  Sapthotharan Nair ,  Sagnik Mukherjee ,  Jay Mundra ,  Fan Du ,  Atharv Tyagi ,  Aparna Garimella

IPC: G06F16/34 ,  G06F16/332 ,  G06N3/04 ,  G06N3/08

Abstract: A text summarization system auto-generates text summarization models using a combination of neural architecture search and knowledge distillation. Given an input dataset for generating/training a text summarization model, neural architecture search is used to sample a search space to select a network architecture for the text summarization model. Knowledge distillation includes fine-tuning a language model for a given text summarization task using the input dataset, and using the fine-tuned language model as a teacher model to inform the selection of the network architecture and the training of the text summarization model. Once a text summarization model has been generated, the text summarization model can be used to generate summaries for given text.

公开(公告)号：US12182829B2

公开(公告)日：2024-12-31

申请号：US17849320

申请日：2022-06-24

Applicant: Adobe Inc.

Inventor： Sarthak Chakraborty ,  Sunav Choudhary ,  Atanu R. Sinha ,  Sapthotharan Krishnan Nair ,  Manoj Ghuhan Arivazhagan ,  Yuvraj ,  Atharva Anand Joshi ,  Atharv Tyagi ,  Shivi Gupta

IPC: G06Q30/0201 ,  G06N3/04 ,  G06Q30/0251

Abstract: A system includes a representation generator subsystem configured to execute a user representation model and a task prediction model to generate a user representation for a user. The user representation model receives user event sequence data comprises a sequence of user interactions with the system. The task prediction model is configured to train the user representation model. The user representation includes a vector of a predetermined size that represents the user event sequence data and is generated by applying the trained user representation model to the user event sequence data. A storage requirement of the user representation is less than a storage space requirement of the user event sequence data. The system includes a data store configured for storing the user representation in a user profile associated with the user.

公开(公告)号：US20240394407A1

公开(公告)日：2024-11-28

申请号：US18324484

申请日：2023-05-26

Applicant: Adobe Inc.

Inventor： Sunav Choudhary ,  Subrata Mitra ,  Sanjay Sukumaran ,  Priyanshu Yadav ,  Munish Gupta ,  Jashn Arora ,  Iftikhar Ahamath Burhanuddin ,  Gautam Choudhary ,  Atharv Tyagi

IPC: G06F21/62

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that implements a secure distributed data collaboration architecture for generating synthetic datasets. For example, the disclosed system sends a request to perform a data collaboration with a first dataset of a first local node and a second dataset of a second local node. The disclosed system receives intermediate feature maps from the local nodes that correspond with the datasets and generates a combined feature map. Further, the disclosed system generates a synthetic dataset from the combined feature map by utilizing a central generative model. Moreover, the synthetic dataset generated by the disclosed system is statistically representative of the first dataset and the second dataset.

公开(公告)号：US20230419339A1

公开(公告)日：2023-12-28

申请号：US17849320

申请日：2022-06-24

Applicant: Adobe Inc.

Inventor： Sarthak Chakraborty ,  Sunav Choudhary ,  Atanu R. Sinha ,  Sapthotharan Krishnan Nair ,  Manoj Ghuhan Arivazhagan ,  Yuvraj ,  Atharva Anand Joshi ,  Atharv Tyagi ,  Shivi Gupta

IPC: G06Q30/02 ,  G06N3/04

CPC classification number: G06Q30/0201 ,  G06N3/04 ,  G06Q30/0269 ,  G06Q30/0255

Abstract: A system includes a representation generator subsystem configured to execute a user representation model and a task prediction model to generate a user representation for a user. The user representation model receives user event sequence data comprises a sequence of user interactions with the system. The task prediction model is configured to train the user representation model. The user representation includes a vector of a predetermined size that represents the user event sequence data and is generated by applying the trained user representation model to the user event sequence data. A storage requirement of the user representation is less than a storage space requirement of the user event sequence data. The system includes a data store configured for storing the user representation in a user profile associated with the user.