ner example using NER with Go (https://github.com/sbl/ner/)

readme.md

• https://github.com/kba/awesome-ocr
• https://github.com/tleyden/open-ocr
• https://github.com/mittagessen/kraken (fork of ocropus)
• https://nlp.stanford.edu/software/CRF-NER.shtml

input.txt

This document is about Cal Ripken and Edgar Allen Poe. It's
being written from a house in Carroll County, specifically Union Bridge.

The author is Craig Wickesser.

ner-using-spacy.py

# $ cd ~
# $ source .env/bin/activate
# $ python
>>> import spacy, io
>>> data = io.open('go/src/github.com/sbl/ner/_example/11231.txt', mode='r', encoding='utf-8').read()
>>> nlp = spacy.load('en')
>>> doc = nlp(data)
>>> for ent in doc.ents:
...   print(ent.text, ent.start_char, ent.end_char, ent.label_)
...
(u'Cal Ripken', 23, 33, u'PERSON')
(u'Edgar Allen Poe', 38, 53, u'PERSON')
(u'\n', 59, 60, u'GPE')
(u'Carroll County', 90, 104, u'GPE')
(u'Union Bridge', 119, 131, u'ORG')
(u'Craig Wickesser', 148, 163, u'PERSON')
(u'\n', 164, 165, u'GPE')

output.txt

2018/01/12 18:07:14 available tags: [PERSON LOCATION ORGANIZATION MISC]
2018/01/12 18:07:14 {Score:1.053429733529049 Tag:0 TagString: Name:Cal Ripken Range:{Start:4 End:6}}
2018/01/12 18:07:14 {Score:0.9948352240424915 Tag:0 TagString: Name:Edgar Allen Poe Range:{Start:7 End:10}}
2018/01/12 18:07:14 {Score:1.0153387737219781 Tag:1 TagString: Name:Carroll County Range:{Start:19 End:21}}
2018/01/12 18:07:14 {Score:0.6087442249127257 Tag:2 TagString: Name:Union Bridge Range:{Start:23 End:25}}
2018/01/12 18:07:14 {Score:1.0389223589760979 Tag:0 TagString: Name:Craig Wickesser Range:{Start:29 End:31}}

stanford-ner-output-3class-eng-model.md

		This document is about
Cal Ripken	PERSON	and
Edgar Allen Poe	PERSON	.

		It 's being written from a house in
Carroll County	LOCATION	, specifically
Union Bridge	LOCATION	.

		The author is
Craig Wickesser	PERSON	.