license: mit
datasets:
- bigbio/chemdner
- ncbi_disease
- jnlpba
- bigbio/n2c2_2018_track2
- bigbio/bc5cdr
language:
- en
metrics:
- precision
- recall
- f1
pipeline_tag: token-classification
tags:
- token-classification
- biology
- medical
- zero-shot
- few-shot
Zero and few shot NER for biomedical texts
Model description
Model takes as input two strings. String1 is NER label. String1 must be phrase for entity. String2 is short text where String1 is searched for semantically. model outputs list of zeros and ones corresponding to the occurance of Named Entity and corresponing to the tokens(tokens given by transformer tokenizer) of the Sring2.
Example of usage
from transformers import AutoTokenizer modelname='./' #modelpath tokenizer = AutoTokenizer.from_pretrained(modelname) ## loading the tokenizer of that model string1='Drug' string2='No recent antibiotics or other nephrotoxins, and no symptoms of UTI with benign UA.' encodings = tokenizer(string1,string2, is_split_into_words=False, padding=True, truncation=True, add_special_tokens=True, return_offsets_mapping=False,max_length=512,return_tensors='pt') from transformers import BertForTokenClassification #AutoModelForPreTraining model = BertForTokenClassification.from_pretrained(modelname, num_labels=2) prediction_logits=model(**encodings)
Code availibility
Code used for training and testing the model is available at https://github.com/br-ai-ns-institute/Zero-ShotNER