The paper 'Automatic knowledge extraction from OCR documents using hierarchical document analysis' was published in 2018.
Notes on verification
Confirmed by ACM Digital Library, DBLP, and the author's institutional repository, all consistently dating the paper to RACS 2018. [tier=silver indep_score=0.875 clusters=2 claim_tier=everyday]
Sources
- A benchmark and evaluation for text extraction from PDF | Proceedings of the 17th ACM/IEEE Joint Conference on Digital Libraries (seed:technology_and_ai)
- https://dblp.org/db/conf/racs/index.html (corroboration)
- https://digitalcommons.kennesaw.edu/dataphdgreylit/12/ (corroboration)