BERN: Neural multi-class biomedical entity recognition and normalization tool for text mining

Donghyeon Kim, Jinhyuk Lee, Chan Ho So, Hwisang Jeon, Minbyul Jeong, Yonghwa Choi, Wonjin Yoon and Jaewoo Kang*

We propose a neural multi-class biomedical entity recognition and normalization tool, BERN, that uses neural network based NER models to recognize unseen entities along with decision rules for resolving entity mention overlaps. Furthermore, various rule-based named-entity normalization models are integrated within BERN to assign a distinct id to each extracted entity.


RESTful API Examples

Single PMID, output in PubAnnotation JSON (default)

3434473691
/bern.korea.ac.kr/pubmed/29446767/json

Single PMID, output in PubTator

/bern.korea.ac.kr/pubmed/29446767/pubtator

Multiple PMIDs

/bern.korea.ac.kr/pubmed/29446767,25681199

Raw texts

For raw texts, use the following Python code.

import requests

def query_raw(text, url="/bern.korea.ac.kr/plain"):
    return requests.post(url, data={'sample_text': text}).json()

if __name__ == '__main__':
    print(query_raw("YOUR TEXT HERE"))

Contacts

If you have any questions or have found a bug, please contact 216-937-0019 and (817) 886-7529