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.

公开(公告)号：US20240152695A1

公开(公告)日：2024-05-09

申请号：US18052693

申请日：2022-11-04

Applicant: ADOBE INC.

Inventor： Tripti Shukla ,  Khyathi Vagolu ,  Sarthak Rout ,  Nakula Neeraje ,  Akhash Nakkonda Amarnath ,  Balaji Vasan Srinivasan

IPC: G06F40/186 ,  G06F16/56 ,  G06F40/295 ,  G06F40/56

CPC classification number: G06F40/186 ,  G06F16/56 ,  G06F40/295 ,  G06F40/56

Abstract: Systems and methods for automatically generating graphic design documents are described. Embodiments include identifying an input text that includes a plurality of phrases; obtaining one or more images based on the input text; encoding an image of the one or more images in a vector space using a multimodal encoder to obtain a vector image representation; encoding a phrase from the plurality of phrases in the vector space using the multimodal encoder to obtain a vector text representation; selecting an image text combination including the image and the phrase by comparing the vector image representation and the vector text representation; selecting a design template from a plurality of candidate design templates based on the image text combination; and generating a document based on the design template, wherein the document includes the at least one image and the at least one phrase.