A YOLOv8x, TrOCR, and GLiNER pipeline converts Italian Supreme Court PDFs into an anonymized topic-modeling dataset, but the reported improvement over OCR-only is not supported by the paper's own Table 13.
Information Systems 112, 102131 (2023) 40
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court
A YOLOv8x, TrOCR, and GLiNER pipeline converts Italian Supreme Court PDFs into an anonymized topic-modeling dataset, but the reported improvement over OCR-only is not supported by the paper's own Table 13.