Table 1 Number of matched cases using OCR text extracted from 10,000 herbarium specimen images.
NER labels | Meaning | Matched cases |
|---|---|---|
en_family_name | Family name of the plants (English) | 1880/10,000 |
'jp_family_name | Family name of the plants (Japanese) | 3124/10,000 |
'en_name | Scientific name | 2637/10,000 |
jp_name | Japanese name | 7009/10,000 |
collect_country | Country | 0/10,000 |
collect_pref | Prefecture | 6830/10,000 |
'collect_city' | Locality | 5802/10,000 |
collect_addr | Street | 3954/10,000 |
collect_date | Date of collection | 0/10,000 |
collect_person | Collector(s) | 4381/10,000 |
collect_number | Collector number | 8757/10,000 |
