import numpy as np
from transformers import AutoModel, AutoTokenizer

model_path = 'snumin44/sap-bert-ko-en'
model = AutoModel.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)

query = '간경화'

targets = [
    'liver cirrhosis',
    '간경변',
    'liver cancer',
    '간암',
    'brain tumor',
    '뇌종양'
]

query_feature = tokenizer(query, return_tensors='pt')
query_outputs = model(**query_feature, return_dict=True)
query_embeddings = query_outputs.pooler_output.detach().numpy().squeeze()

def cos_sim(A, B):
    return np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B))

for idx, target in enumerate(targets):
    target_feature = tokenizer(target, return_tensors='pt')
    target_outputs = model(**target_feature, return_dict=True)
    target_embeddings = target_outputs.pooler_output.detach().numpy().squeeze()
    similarity = cos_sim(query_embeddings, target_embeddings)
    print(f"Similarity between query and target {idx}: {similarity:.4f}")

Similarity between query and target 0: 0.7145
Similarity between query and target 1: 0.7186
Similarity between query and target 2: 0.6183
Similarity between query and target 3: 0.6972
Similarity between query and target 4: 0.3929
Similarity between query and target 5: 0.4260

Citing

@inproceedings{liu2021self,
	title={Self-Alignment Pretraining for Biomedical Entity Representations},
	author={Liu, Fangyu and Shareghi, Ehsan and Meng, Zaiqiao and Basaldella, Marco and Collier, Nigel},
	booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
	pages={4228--4238},
	month = jun,
	year={2021}
}