TEDS
A table similarity evaluation metric based on tree edit distance that models table structure and content as a tree and then computes the edit distance; widely used in table recognition evaluation.
Timeline (last 90 days)
OCR commonly uses character error rate (CER) and word error rate (WER) as evaluation metrics; document AI focuses more on field-level accuracy and the TEDS score for table reconstruction.
Spartan currently lacks formal benchmark evaluation (e.g., using GriTS or TEDS on ICDAR 2013/PubTables-1M/FinTabNet), which is its biggest shortcoming.
All Facts (2)
OCR commonly uses character error rate (CER) and word error rate (WER) as evaluation metrics; document AI focuses more on field-level accuracy and the TEDS score for table reconstruction.
50%UnverifiedSpartan currently lacks formal benchmark evaluation (e.g., using GriTS or TEDS on ICDAR 2013/PubTables-1M/FinTabNet), which is its biggest shortcoming.
50%