I want to use “grouped_entities” in the huggingface pipeline for ner task, how to do that?

问题

I want to use "grouped_entities" in the huggingface pipeline for ner task. However having issues doing that.

I do look the following link on git but this did not help: https://github.com/huggingface/transformers/pull/4987

回答1:

I got the answer its very straight forward in the transformer v4.0.0. Previously I was using older version of transformer package. example:

from transformers import AutoTokenizer, 
 AutoModelForTokenClassification,TokenClassificationPipeline

 from transformers import pipeline 

tokenizer = AutoTokenizer.from_pretrained("fine_tune_model_path")
model = AutoModelForTokenClassification.from_pretrained("fine_tune_model_path")
nlp=pipeline(task='ner',model=model,
 tokenizer=tokenizer,grouped_entities=True)

来源：https://stackoverflow.com/questions/65353104/i-want-to-use-grouped-entities-in-the-huggingface-pipeline-for-ner-task-how-t