公开(公告)号：US11487971B2

公开(公告)日：2022-11-01

申请号：US17073258

申请日：2020-10-16

申请人： Adobe Inc.

发明人： Navita Goyal ,  Balaji Vasan Srinivasan ,  Anandha velu Natarajan ,  Abhilasha Sancheti

IPC分类号： G06F17/00 ,  G06K9/62 ,  G06F40/205 ,  G06K9/00 ,  G06V30/414 ,  G06F40/40

摘要： In some embodiments, a style transfer computing system generates a set of discriminator models corresponding to a set of styles based on a set of training datasets labeled for respective styles. The style transfer computing system further generates a style transfer language model for a target style combination that includes multiple target styles from the set of styles. The style transfer language model includes a cascaded language model and multiple discriminator models selected from the set of discriminator models. The style transfer computing system trains the style transfer language model to minimize a loss function containing a loss term for the cascaded language model and multiple loss terms for the multiple discriminator models. For a source sentence and a given target style combination, the style transfer computing system applies the style transfer language model on the source sentence to generate a target sentence in the given target style combination.

公开(公告)号：US20220171935A1

公开(公告)日：2022-06-02

申请号：US17108424

申请日：2020-12-01

申请人： Adobe Inc.

发明人： Navita Goyal ,  Vipul Shankhpal ,  Priyanshu Gupta ,  Ishika Singh ,  Baldip Singh Bijlani ,  Anandha velu Natarajan

IPC分类号： G06F40/289 ,  G06F40/35 ,  G06N5/02 ,  G06F16/901 ,  G06F16/9038

摘要： This disclosure involves executing machine-learning techniques for transforming or otherwise processing electronic data. This disclosure, for example, relates to executing machine-learning techniques to generate data-verification indicators that augment electronic documents to represent the veracity of text. The machine-learning techniques include neural networks trained to retrieve and analyze evidence regarding content of electronic documents and to generate indicators of veracity to be displayed with that content via electronic reading software.

公开(公告)号：US11687716B2

公开(公告)日：2023-06-27

申请号：US17108424

申请日：2020-12-01

申请人： Adobe Inc.

发明人： Navita Goyal ,  Vipul Shankhpal ,  Priyanshu Gupta ,  Ishika Singh ,  Baldip Singh Bijlani ,  Anandha velu Natarajan

IPC分类号： G06F40/289 ,  G06F40/35 ,  G06F16/9038 ,  G06F16/901 ,  G06N5/022 ,  G06F16/35 ,  G06F40/30 ,  G06N20/00 ,  G06N5/02

CPC分类号： G06F40/289 ,  G06F16/353 ,  G06F16/9024 ,  G06F16/9038 ,  G06F40/30 ,  G06F40/35 ,  G06N5/022 ,  G06N20/00 ,  G06N5/02

摘要： This disclosure involves executing machine-learning techniques for transforming or otherwise processing electronic data. This disclosure, for example, relates to executing machine-learning techniques to generate data-verification indicators that augment electronic documents to represent the veracity of text. The machine-learning techniques include neural networks trained to retrieve and analyze evidence regarding content of electronic documents and to generate indicators of veracity to be displayed with that content via electronic reading software.

公开(公告)号：US20230153533A1

公开(公告)日：2023-05-18

申请号：US17525311

申请日：2021-11-12

申请人： ADOBE INC.

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

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

CPC分类号： G06F40/289 ,  G06F40/211 ,  G06F40/42 ,  G06K9/6215

摘要： 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：US20200081964A1

公开(公告)日：2020-03-12

申请号：US16123966

申请日：2018-09-06

申请人： Adobe Inc.

发明人： Pranav Ravindra Maneriker ,  Vishwa Vinay ,  Sopan Khosla ,  Niyati Himanshu Chhaya ,  Natwar Modani ,  Cedric Huesler ,  Balaji Vasan Srinivasan ,  Anandha velu Natarajan

IPC分类号： G06F17/24 ,  G06F17/27 ,  G06F17/21 ,  G06F15/18

摘要： A fact replacement and style consistency tool is described. Rather than rely heavily on human involvement to replace facts and maintain consistent styles across multiple digital documents, the described change management system identifies factual and stylistic inconsistencies between these documents, in part, using natural language processing techniques. Once these inconsistencies are identified, the change management system generates a user interface that includes indications of the inconsistencies and information describing them, e.g., an indication noting not only a type of inconsistency but also presenting a first portion and at least a second portion of the multiple documents that are factually inconsistent. By automatically identifying these factual and stylistic inconsistencies across multiple documents and presenting indications of such cross-document inconsistencies, the described change management system eliminates human errors in connection with maintaining factual and stylistic consistency over a body of documents.

公开(公告)号：US11741190B2

公开(公告)日：2023-08-29

申请号：US17902586

申请日：2022-09-02

申请人： Adobe Inc.

发明人： Navita Goyal ,  Balaji Vasan Srinivasan ,  Anandha velu Natarajan ,  Abhilasha Sancheti

IPC分类号： G06F17/00 ,  G06F18/214 ,  G06F40/205 ,  G06V30/414 ,  G06F40/40

CPC分类号： G06F18/2148 ,  G06F18/2155 ,  G06F40/205 ,  G06F40/40 ,  G06V30/414 ,  G06F2218/04

摘要： In some embodiments, a style transfer computing system receives, from a computing device, an input text and a request to transfer the input text to a target style combination including a set of target styles. The system applies a style transfer language model associated with the target style combination to the input text to generate a transferred text in the target style combination. The style transfer language model comprises a cascaded language model configured to generate the transferred text. The cascaded language model is trained using a set of discriminator models corresponding to the set of target styles. The system provides, to the computing device, the transferred text.

公开(公告)号：US20220414400A1

公开(公告)日：2022-12-29

申请号：US17902586

申请日：2022-09-02

申请人： Adobe Inc.

发明人： Navita Goyal ,  Balaji Vasan Srinivasan ,  Anandha velu Natarajan ,  Abhilasha Sancheti

IPC分类号： G06K9/62 ,  G06F40/40 ,  G06K9/00 ,  G06V30/414 ,  G06F40/205

摘要： In some embodiments, a style transfer computing system receives, from a computing device, an input text and a request to transfer the input text to a target style combination including a set of target styles. The system applies a style transfer language model associated with the target style combination to the input text to generate a transferred text in the target style combination. The style transfer language model comprises a cascaded language model configured to generate the transferred text. The cascaded language model is trained using a set of discriminator models corresponding to the set of target styles. The system provides, to the computing device, the transferred text.

公开(公告)号：US20220121879A1

公开(公告)日：2022-04-21

申请号：US17073258

申请日：2020-10-16

申请人： Adobe Inc.

发明人： Navita Goyal ,  Balaji Vasan Srinivasan ,  Anandha velu Natarajan ,  Abhilasha Sancheti

IPC分类号： G06K9/62 ,  G06K9/00 ,  G06F40/205

摘要： In some embodiments, a style transfer computing system generates a set of discriminator models corresponding to a set of styles based on a set of training datasets labeled for respective styles. The style transfer computing system further generates a style transfer language model for a target style combination that includes multiple target styles from the set of styles. The style transfer language model includes a cascaded language model and multiple discriminator models selected from the set of discriminator models. The style transfer computing system trains the style transfer language model to minimize a loss function containing a loss term for the cascaded language model and multiple loss terms for the multiple discriminator models. For a source sentence and a given target style combination, the style transfer computing system applies the style transfer language model on the source sentence to generate a target sentence in the given target style combination.

公开(公告)号：US11194958B2

公开(公告)日：2021-12-07

申请号：US16123966

申请日：2018-09-06

申请人： Adobe Inc.

发明人： Pranav Ravindra Maneriker ,  Vishwa Vinay ,  Sopan Khosla ,  Niyati Himanshu Chhaya ,  Natwar Modani ,  Cedric Huesler ,  Balaji Vasan Srinivasan ,  Anandha velu Natarajan

IPC分类号： G06F40/10 ,  G06F40/166 ,  G06N20/00 ,  G06F40/30 ,  G06F40/109 ,  G06F40/103 ,  G06F40/253

摘要： A fact replacement and style consistency tool is described. Rather than rely heavily on human involvement to replace facts and maintain consistent styles across multiple digital documents, the described change management system identifies factual and stylistic inconsistencies between these documents, in part, using natural language processing techniques. Once these inconsistencies are identified, the change management system generates a user interface that includes indications of the inconsistencies and information describing them, e.g., an indication noting not only a type of inconsistency but also presenting a first portion and at least a second portion of the multiple documents that are factually inconsistent. By automatically identifying these factual and stylistic inconsistencies across multiple documents and presenting indications of such cross-document inconsistencies, the described change management system eliminates human errors in connection with maintaining factual and stylistic consistency over a body of documents.