3

Is there a freely available list of geographical entities, like cities, provinces (in China and abroad), names of rivers, mountains, etc.?

I am looking for something like GeoNames, but it doesn't have to be that feature rich.

I would like to use this for named-entity recognition.

3

After some research into this I found this website: http://docs.bosonnlp.com/ner.html. If you set up an account on their website, you can use their NER functionality (because you need an API Token. I tried their Python example

import json
import requests


NER_URL = 'http://api.bosonnlp.com/ner/analysis'


s = ['对于该小孩是不是郑尚金的孩子,目前已做亲子鉴定,结果还没出来,'
     '纪检部门仍在调查之中。成都商报记者 姚永忠']
data = json.dumps(s)
headers = {'X-Token': 'YOUR_API_TOKEN'}
resp = requests.post(NER_URL, headers=headers, data=data)


for item in resp.json():
    for entity in item['entity']:
        print(''.join(item['word'][entity[0]:entity[1]]), entity[2])

And got back:

郑尚金 person_name
成都商报 product_name
姚永忠 person_name

However, it seems they have a 500 daily request limit.

Doing some more research, they seem to have a publicly available list of names they use for their text comparison (The link is under 命名实体数据). That might be what you're looking for.

2

外國地名譯名

外国地名译名手册 / Mainland

https://zh.wikipedia.org/wiki/%E5%A4%96%E5%9B%BD%E5%9C%B0%E5%90%8D%E8%AF%91%E5%90%8D%E6%89%8B%E5%86%8C

  • Mainland, simplified characters, but can only find scanned copies online

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.