PAGED: A Benchmark for Procedural Graphs Extraction from Documents.
Weihong DuWenrui LiaoHongru LiangWenqiang LeiPublished in: ACL (1) (2024)
Keyphrases
- document collections
- information retrieval
- web documents
- information retrieval systems
- text documents
- information extraction
- legal documents
- document classification
- relevant documents
- graph theory
- xml documents
- database
- multimedia documents
- graph theoretic
- automatic extraction
- document retrieval
- metadata
- keywords
- graph databases
- object oriented
- vector space
- web data
- ranked list
- bipartite graph
- graph representation
- retrieval systems
- user queries
- textual content
- document structure