Downloads · 30 days
0
dental-paper-classifier
gowrisivaramakrishnan/dental-paper-classifier
dental-paper-classifier is a machine learning model from gowrisivaramakrishnan. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
tags: - dentistry - text-classification - bert - study-design - biomedical-nlp ---
Access
Public
Updated Sep 28, 2026
Repo size
9.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.1 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 8, 2026
- Updated
- Sep 28, 2026
- SHA
- dfd12111
Model card
From the Hugging Face model README
tags:
- dentistry
- text-classification
- bert
- study-design
- biomedical-nlp
Dental Paper Classifier
Fine-tuned BERT-based models for automated classification of dental research papers into six study-design categories using titles and abstracts.
Study Design Categories
- Case-control study
- Case report/series
- Cross-sectional study
- Prospective/Retrospective cohort
- Randomised/quasi-randomised/pragmatic trials
- Systematic review/Meta-analysis
Models
Seven BERT variants were fine-tuned in two input-format configurations:
| Model | Hugging Face ID |
|---|---|
| BERT-base | bert-base-uncased |
| SciBERT | allenai/scibert_scivocab_uncased |
| BioBERT | dmis-lab/biobert-v1.1 |
| Bio_ClinicalBERT | emilyalsentzer/Bio_ClinicalBERT |
| BiomedBERT | microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract |
| PubMedBERT | microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext |
| BioLinkBERT | michiyasunaga/BioLinkBERT-base |
Configurations
with_sep/— title and abstract concatenated with the[SEP]special tokenwithout_sep/— title and abstract concatenated with a space
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
subfolder = "with_sep/pubmedbert" # or "without_sep/pubmedbert"
model = AutoModelForSequenceClassification.from_pretrained(
"gowrisivaramakrishnan/dental-paper-classifier",
subfolder=subfolder
)
tokenizer = AutoTokenizer.from_pretrained(
"gowrisivaramakrishnan/dental-paper-classifier",
subfolder=subfolder
)
# Example inference
text = "Title [SEP] Abstract"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
outputs = model(**inputs)
predicted_class = outputs.logits.argmax(dim=1).item()
license: mit
---
- Created
- Jul 8, 2026
- Updated
- Sep 28, 2026