Patent · US Active

Enhanced document visual question answering system via hierarchical attention

US12346655B2 · kind B2 · utility

0Cited by
2References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 17, 2021
Grant dateJul 1, 2025
Priority date
Expiry dateMay 15, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/022
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.