公开(公告)号：US11954431B2

公开(公告)日：2024-04-09

申请号：US17522790

申请日：2021-11-09

Applicant: Adobe Inc.

Inventor： Suryateja Bv ,  Vishwa Vinay ,  Niyati Himanshu Chhaya ,  Navita Goyal ,  Elaine Chao ,  Balaji Vasan Srinivasan ,  Aparna Garimella

IPC: G06F40/194 ,  G06F16/901 ,  G06F16/93 ,  G06F40/14

CPC classification number: G06F40/194 ,  G06F16/9027 ,  G06F16/93 ,  G06F40/14

Abstract: Embodiments are disclosed for generating an intelligent change summary are described. In some embodiments, a method of generating an intelligent change summary includes obtaining a representation of a plurality of versions of a document, determining a distance score based on a comparison of a first of version of the document and a second version of the document, the distance score representing a magnitude of changes made from the first version of the document to the second version of the document, and generating a change summary of the document based on the distance score.

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：US12159109B2

公开(公告)日：2024-12-03

申请号：US17525311

申请日：2021-11-12

Applicant: ADOBE INC.

Inventor： Aniruddha Mahapatra ,  Sharmila Reddy Nangi ,  Aparna Garimella ,  Anandha velu Natarajan

IPC: G06F40/289 ,  G06F18/214 ,  G06F40/211 ,  G06F40/284 ,  G06F40/30 ,  G06F40/42 ,  G06F18/22

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for pre-training entity extraction models to facilitate domain adaptation in resource-constrained domains. In an example embodiment, a first machine learning model is used to encode sentences of a source domain corpus and a target domain corpus into sentence embeddings. The sentence embeddings of the target domain corpus are combined into a target corpus embedding. Training sentences from the source domain corpus within a threshold of similarity to the target corpus embedding are selected. A second machine learning model is trained on the training sentences selected from the source domain corpus.

公开(公告)号：US20240378370A1

公开(公告)日：2024-11-14

申请号：US18316674

申请日：2023-05-12

Applicant: Adobe Inc.

Inventor： Aparna Garimella ,  Anandhavelu Natarajan ,  Abhilasha Sancheti ,  Sarthak Chauhan ,  Prateek Agarwal ,  Harshit Varma

IPC: G06F40/166 ,  G06F40/20 ,  G06F40/40 ,  G06N3/0455 ,  G06N3/0475 ,  G06N3/092

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a long-range event relation dataset by augmenting a digital document with a set of synthetic sentences. For example, the disclosed systems access a digital document from a short-range event relation dataset that includes an event pair. In some embodiments, the disclosed systems generate a set of synthetic sentences utilizing a generative language model for inserting within the digital document between the event pair to satisfy a long-range event relation threshold. In these or other embodiments, the disclosed systems generate a long-range event relation dataset by augmenting the digital document within the short-range event relation dataset to include the set of synthetic sentences. In certain cases, the disclosed systems generate an event relation extraction model to determine long-range event relations by learning model parameters for the event relation extraction model from the long-range event relation dataset.

公开(公告)号：US20240119220A1

公开(公告)日：2024-04-11

申请号：US18045551

申请日：2022-10-11

Applicant: ADOBE INC.

Inventor： Vinay Aggarwal ,  Aparna Garimella ,  Ananya Ganesh ,  Niyati Himanshu Chhaya ,  Nandakishore Kambhatla

IPC: G06F40/166 ,  G06F40/289 ,  G06F40/30 ,  G06N3/08

CPC classification number: G06F40/166 ,  G06F40/289 ,  G06F40/30 ,  G06N3/082

Abstract: Systems and methods for text simplification are described. Embodiments of the present disclosure identify a simplified text that includes original information from a complex text and additional information that is not in the complex text. Embodiments then compute an entailment score for each sentence of the simplified text using a neural network, wherein the entailment score indicates whether the sentence of the simplified text includes information from a sentence of the complex text corresponding to the sentence of the simplified text. Then, embodiments generate a modified text based on the entailment score, the simplified text, and the complex text, wherein the modified text includes the original information and excludes the additional information. Embodiments may then present the modified text to a user via a user interface.

公开(公告)号：US20230161952A1

公开(公告)日：2023-05-25

申请号：US17456143

申请日：2021-11-22

Applicant: ADOBE INC.

Inventor： Aparna Garimella ,  Sumit Shekhar ,  Bhanu Prakash Reddy Guda ,  Vinay Aggarwal ,  Vlad Ion Morariu ,  Ashutosh Mehra

IPC: G06F40/174 ,  G06F40/284 ,  G06F40/30 ,  G06N3/04

CPC classification number: G06F40/174 ,  G06F40/284 ,  G06F40/30 ,  G06N3/0454

Abstract: Embodiments provide systems, methods, and computer storage media for extracting semantic labels for field widgets of form fields in unfilled forms. In some embodiments, a processing device accesses a representation of a fillable widget of a form field of an unfilled form. The processing device generates an encoded input representing text and layout of a sequence of tokens in a neighborhood of the fillable widget. The processing device uses a machine learning model to extract a semantic label representing a field type of the fillable widget in view of the encoded input. The processing device causes execution of an action using the semantic label.

公开(公告)号：US20230153533A1

公开(公告)日：2023-05-18

申请号：US17525311

申请日：2021-11-12

Applicant: ADOBE INC.

Inventor： Aniruddha Mahapatra ,  Sharmila Reddy Nangi ,  Aparna Garimella ,  Anandha velu Natarajan

IPC: G06F40/289 ,  G06F40/211 ,  G06F40/42

CPC classification number: G06F40/289 ,  G06F40/211 ,  G06F40/42 ,  G06K9/6215

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for pre-training entity extraction models to facilitate domain adaptation in resource-constrained domains. In an example embodiment, a first machine learning model is used to encode sentences of a source domain corpus and a target domain corpus into sentence embeddings. The sentence embeddings of the target domain corpus are combined into a target corpus embedding. Training sentences from the source domain corpus within a threshold of similarity to the target corpus embedding are selected. A second machine learning model is trained on the training sentences selected from the source domain corpus.

公开(公告)号：US20220129621A1

公开(公告)日：2022-04-28

申请号：US17079681

申请日：2020-10-26

Applicant: Adobe Inc.

Inventor： Bhanu Prakash Reddy Guda ,  Niyati Chhaya ,  Aparna Garimella

IPC: G06F40/166 ,  G10L25/63 ,  G06N20/00 ,  G06K9/62

Abstract: Certain embodiments involve using machine-learning tools that include Bidirectional Encoder Representations from Transformers (“BERT”) language models for predicting emotional responses to text by, for example, target readers having certain demographics. For instance, a machine-learning model includes, at least, a BERT encoder and a classification module that is trained to predict demographically specific emotional responses. The BERT encoder encodes the input text into an input text vector. The classification module generates, from the input text vector and an input demographics vector representing a demographic profile of the reader, an emotional response score.

公开(公告)号：US12118295B2

公开(公告)日：2024-10-15

申请号：US18045551

申请日：2022-10-11

Applicant: ADOBE INC.

Inventor： Vinay Aggarwal ,  Aparna Garimella ,  Ananya Ganesh ,  Niyati Himanshu Chhaya ,  Nandakishore Kambhatla

IPC: G06F17/00 ,  G06F40/166 ,  G06F40/289 ,  G06F40/30 ,  G06N3/082

CPC classification number: G06F40/166 ,  G06F40/289 ,  G06F40/30 ,  G06N3/082

Abstract: Systems and methods for text simplification are described. Embodiments of the present disclosure identify a simplified text that includes original information from a complex text and additional information that is not in the complex text. Embodiments then compute an entailment score for each sentence of the simplified text using a neural network, wherein the entailment score indicates whether the sentence of the simplified text includes information from a sentence of the complex text corresponding to the sentence of the simplified text. Then, embodiments generate a modified text based on the entailment score, the simplified text, and the complex text, wherein the modified text includes the original information and excludes the additional information. Embodiments may then present the modified text to a user via a user interface.

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.