End-to-End Hyper-Relational Information Extraction for Engineering Diagrams via Dynamically Tokenized Relation Transformer
An end-to-end information extraction framework based on the Dynamically Tokenized Relation Transformer (DTRT), which can dynamically reduce received image to-kens, filter redundant information, and efficiently extract structural knowledge to construct hyper-relational knowledge graphs is proposed.
Tianyou Bai, Yan-Ming Zhang, Zi-Xiang Zhang et al.
· 0 citations