Downloads · 30 days
68
55% of all-time downloads
phuong-tk-nguyen/vipubmed-deberta-xsmall-en-vimedner-ner-vi
vipubmed-deberta-xsmall-en-vimedner-ner-vi is a token classification model from phuong-tk-nguyen. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as cc-by-4.0.
Fine-tuned manhtt-079/vipubmed-deberta-xsmall for Vietnamese biomedical Named Entity Recognition with UMLS semantic-type labels, trained on the Vietnamese split of En-ViMedNER.
Downloads · 30 days
68
55% of all-time downloads
All-time downloads
123
Public
Parameters
70.7M
283 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors283 MB · 97%
From the Hugging Face model README
Fine-tuned manhtt-079/vipubmed-deberta-xsmall
for Vietnamese biomedical Named Entity Recognition with UMLS semantic-type labels, trained on
the Vietnamese split of En-ViMedNER.
Vietnamese input should be word-segmented with VnCoreNLP (RDRSegmenter) before inference, since the model was fine-tuned on word-segmented text.
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
model_id = "phuong-tk-nguyen/vipubmed-deberta-xsmall-en-vimedner-ner-vi"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForTokenClassification.from_pretrained(model_id)
ner = pipeline("token-classification", model=model, tokenizer=tokenizer,
aggregation_strategy="simple")
segmented_text = "Nhóm chẩn_đoán phổ_biến nhất dẫn đến nhập_viện là các bệnh_lý tim_mạch."
print(ner(segmented_text))
# [{'entity_group': 'T033', 'score': np.float32(0.54567045), 'word': 'chẩn_đoán', 'start': 4, 'end': 14}, {'entity_group': 'T058', 'score': np.float32(0.94203985), 'word': 'nhập_viện', 'start': 36, 'end': 46}, {'entity_group': 'T038', 'score': np.float32(0.7735123), 'word': 'các bệnh_lý tim', 'start': 49, 'end': 65}]
Another model variation: phuong-tk-nguyen/vipubmed-deberta-base-en-vimedner-ner-vi