公开(公告)号：US20240427995A1

公开(公告)日：2024-12-26

申请号：US18339883

申请日：2023-06-22

Applicant: Adobe Inc.

Inventor： Jiuxiang GU ,  Ryan ROSSI ,  Gaurav VERMA ,  Christopher TENSMEYER ,  Ani NENKOVA

IPC: G06F40/289 ,  G06F40/205 ,  G06T11/60

Abstract: A method includes receiving a text to be used for generating an image. The method further includes determining whether the text is a visual text using a machine learning model trained to classify whether an input text is non-visual text or visual text. The method further includes responsive to determining that the text is a visual text, generating the image using a second machine learning model based on the text. The method further includes displaying the image and the text.

公开(公告)号：US20250078350A1

公开(公告)日：2025-03-06

申请号：US18460401

申请日：2023-09-01

Applicant: Adobe Inc.

Inventor： Christopher TENSMEYER ,  Fuxiao LIU ,  Hao TAN ,  Ani NENKOVA

IPC: G06T11/60 ,  G06F3/04842 ,  G06F3/04845

Abstract: Embodiments are disclosed for reflowing documents to display semantically related content. The method may include receiving a request to view a document that includes body text and one or more images. A trimodal document relationship model identifies relationships between segments of the body text and the one or more images. A linearized view of the document is generated based on the relationships and the linearized view is caused to be displayed on a user device.

公开(公告)号：US20230334244A1

公开(公告)日：2023-10-19

申请号：US17724349

申请日：2022-04-19

Applicant: Adobe Inc.

Inventor： Christopher TENSMEYER ,  Danilo Neves Ribeiro ,  Varun MANJUNATHA ,  Nedim LIPKA ,  Ani NENKOVA

IPC: G06F40/284 ,  G06N20/20 ,  G06F16/2453 ,  G06F40/226

CPC classification number: G06F40/284 ,  G06N20/20 ,  G06F16/24535 ,  G06F40/226

Abstract: Embodiments are disclosed for performing fact correction of natural language sentences using data tables. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input sentence, tokenizing elements of the input sentence, and identifying, by a first machine learning model, a data table associated with the input sentence. The systems and methods further comprise a second machine learning model identifying a tokenized element of the input sentence that renders the input sentence false based on the data table and masking the tokenized element of the tokenized input sentence that renders the input sentence false. The systems and method further includes a third machine learning model predicting a new value for the masked tokenized element based on the input sentence with the masked tokenized element and the identified data table and providing an output including a modified input sentence with the new value.