S-PubMedBert-MS-MARCO

pritamdeka/S-PubMedBert-MS-MARCO

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

This is the microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext model which has been fine-tuned over the MS-MARCO dataset using sentence-transformers framework. It can be used for the information retrieval task in the medical/health text domain.

Usage (Sentence-Transformers)

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

pip install -U sentence-transformers

Then you can use the model like this:

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

model = SentenceTransformer('pritamdeka/S-PubMedBert-MS-MARCO')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

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('pritamdeka/S-PubMedBert-MS-MARCO')
model = AutoModel.from_pretrained('pritamdeka/S-PubMedBert-MS-MARCO')

# 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, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

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

<!--- ## Evaluation Results --> <!--- Describe how your model was evaluated --> <!--- For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) -->

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 31434 with parameters:

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

Loss:

beir.losses.margin_mse_loss.MarginMSELoss

Parameters of the fit()-Method:

{
    "callback": null,
    "epochs": 2,
    "evaluation_steps": 10000,
    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "correct_bias": false,
        "eps": 1e-06,
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 1000,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 350, '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})
)

Citing & Authors

<!--- Describe where people can find more information -->

@article{deka2022improved,
  title={Improved Methods To Aid Unsupervised Evidence-Based Fact Checking For Online Health News},
  author={Deka, Pritam and Jurek-Loughrey, Anna and Deepak, P},
  journal={Journal of Data Intelligence},
  volume={3},
  number={4},
  pages={474--504},
  year={2022}
}