Wikimedical Sent Biobert

🚀 WikiMedical_sent_biobert

This is a sentence-transformers model that maps sentences and paragraphs to a 768-dimensional dense vector space, useful for tasks like clustering and semantic search.

This model belongs to the sentence-similarity pipeline and is tagged with sentence-transformers, feature-extraction, sentence-similarity, and transformers. It is trained on the nuvocare/WikiMedical_sentence_similarity dataset.

WikiMedical_sent_bert is based on the dmis-lab/biobert-base-cased-v1.2 backbone and has been trained on the WikiMedical_sentence_simialrity dataset. It can predict whether two medical texts are related to the same Wikipedia page.

🚀 Quick Start

✨ Features

• Maps sentences & paragraphs to a 768 dimensional dense vector space.
• Can be used for clustering or semantic search.
• Able to predict whether two medical texts are related to the same wikipedia page.

📦 Installation

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

If you have sentence-transformers installed:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('nuvocare/WikiMedical_sent_biobert')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Without sentence-transformers, you can use the model like this:

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('WikiMedical_sent_biobert')
model = AutoModel.from_pretrained('WikiMedical_sent_biobert')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

📚 Documentation

Evaluation Results

The model is evaluated on the test set of WikiMedical_sentence_similarity. It achieves:

• A cosine spearman score of 0.87
• A cosine pearson score of 0.95

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training

The model was trained with the following parameters:

DataLoader: torch.utils.data.dataloader.DataLoader of length 3170 with parameters:

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss: sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss

Parameters of the fit()-Method:

{
    "epochs": 2,
    "evaluation_steps": 2000,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 300,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

📄 License

No license information provided.

Citing & Authors

Samuel Chaineau