Method: BERT with Multi-task Confidence Prediction - Samples list - Task 3 - Key Information Extraction - ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction - Robust Reading Competition

< previous

Page of 18

next >

View

Thumbnails
Table

Sample	Results
	Default
	Recall	Precision	Hmean
41	75.00%	75.00%	75.00%
42	100.00%	100.00%	100.00%
43	75.00%	75.00%	75.00%
44	50.00%	50.00%	50.00%
45	75.00%	75.00%	75.00%
46	50.00%	50.00%	50.00%
47	100.00%	100.00%	100.00%
48	100.00%	100.00%	100.00%
49	100.00%	100.00%	100.00%
50	75.00%	75.00%	75.00%
51	25.00%	25.00%	25.00%
52	100.00%	100.00%	100.00%
53	75.00%	75.00%	75.00%
54	75.00%	75.00%	75.00%
55	75.00%	75.00%	75.00%
56	50.00%	50.00%	50.00%
57	50.00%	50.00%	50.00%
58	100.00%	100.00%	100.00%
59	50.00%	50.00%	50.00%
60	75.00%	75.00%	75.00%

Download full table (.csv)

Results