公开(公告)号：US20230153531A1

公开(公告)日：2023-05-18

申请号：US17528972

申请日：2021-11-17

Applicant: ADOBE INC.

Inventor： Shijie Geng ,  Christopher Tensmeyer ,  Curtis Michael Wigington ,  Jiuxiang Gu

IPC: G06F40/284 ,  G06N3/04 ,  G06F16/2452

CPC classification number: G06F40/284 ,  G06F16/24526 ,  G06N3/04

Abstract: Systems and methods for performing Document Visual Question Answering tasks are described. A document and query are received. The document encodes document tokens and the query encodes query tokens. The document is segmented into nested document sections, lines, and tokens. A nested structure of tokens is generated based on the segmented document. A feature vector for each token is generated. A graph structure is generated based on the nested structure of tokens. Each graph node corresponds to the query, a document section, a line, or a token. The node connections correspond to the nested structure. Each node is associated with the feature vector for the corresponding object. A graph attention network is employed to generate another embedding for each node. These embeddings are employed to identify a portion of the document that includes a response to the query. An indication of the identified portion of the document is be provided.