CODEWITHSUNDEEP
pythonstanford-nlpnamed-entity-recognition
Sadia Sami
Sadia Sami

Reputation: 13

Integrate custom trained NER model with existing default model in Stanford CoreNLP

I have trained corpus by following below link.

https://www.sicara.ai/blog/2018-04-25-python-train-model-NTLK-stanford-ner-tagger

Dataset is of some health blog (in English language) on which I've trained. I am successfully able to run this model on my new unseen text.

Problem: The problem I am facing is that I want to run my custom English NER model along with default English model in Stanford CoreNLP.

Desired Outcome: I want Stanford default model to run in sequential manner just after my own custom model NER model to handle those entities in English that are missed by my own model.

Upvotes: 1

Views: 387

Answers (1)

StanfordNLPHelp
StanfordNLPHelp

Reputation: 8739

 ner.model = /path/to/custom-model.ser.gz,edu/stanford/nlp/models/ner/english.all.3class.distsim.crf.ser.gz,edu/stanford/nlp/models/ner/english.muc.7class.distsim.crf.ser.gz,edu/stanford/nlp/models/ner/english.conll.4class.distsim.crf.ser.gz

There is more info here:

https://stanfordnlp.github.io/CoreNLP/api.html

https://stanfordnlp.github.io/CoreNLP/cmdline.html

Upvotes: 0

Related Questions