A VLM-based framework with retrieval-augmented generation parses tombstone photos into structured semantic graphs, reaching 89.5 Smatch F1 versus 36.1 for the prior OCR pipeline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Modal Semantic Parsing for the Interpretation of Tombstone Inscriptions
A VLM-based framework with retrieval-augmented generation parses tombstone photos into structured semantic graphs, reaching 89.5 Smatch F1 versus 36.1 for the prior OCR pipeline.