language: multilingual
tags:
- biomedical
- lexical-semantics
- cross-lingual
datasets:
- UMLS
[news] A cross-lingual extension of SapBERT will appear in the main onference of ACL 2021! [news] SapBERT will appear in the conference proceedings of NAACL 2021!
SapBERT-XLMR
SapBERT (Liu et al. 2021) trained with UMLS 2020AB, using xlm-roberta-large as the base model. Please use [CLS] as the representation of the input.
Extracting embeddings from SapBERT
The following script converts a list of strings (entity names) into embeddings.
import numpy as np
import torch
from tqdm.auto import tqdm
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("cambridgeltl/SapBERT-from-PubMedBERT-fulltext")
model = AutoModel.from_pretrained("cambridgeltl/SapBERT-from-PubMedBERT-fulltext").cuda()
# replace with your own list of entity names
all_names = ["covid-19", "Coronavirus infection", "high fever", "Tumor of posterior wall of oropharynx"]
bs = 128 # batch size during inference
all_embs = []
for i in tqdm(np.arange(0, len(all_names), bs)):
toks = tokenizer.batch_encode_plus(all_names[i:i+bs],
padding="max_length",
max_length=25,
truncation=True,
return_tensors="pt")
toks_cuda = {}
for k,v in toks.items():
toks_cuda[k] = v.cuda()
cls_rep = model(**toks_cuda)[0][:,0,:] # use CLS representation as the embedding
all_embs.append(cls_rep.cpu().detach().numpy())
all_embs = np.concatenate(all_embs, axis=0)
For more details about training and eval, see SapBERT github repo.
Citation
@inproceedings{liu2021learning,
title={Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking},
author={Liu, Fangyu and Vuli{\'c}, Ivan and Korhonen, Anna and Collier, Nigel},
booktitle={Proceedings of ACL-IJCNLP 2021},
month = aug,
year={2021}
}