FremyCompany / BioLORD-STAMB2-v1

huggingface.co
Total runs: 75
24-hour runs: 0
7-day runs: -516
30-day runs: -612
Model's Last Updated: November 27 2023
sentence-similarity

Introduction of BioLORD-STAMB2-v1

Model Details of BioLORD-STAMB2-v1

FremyCompany/BioLORD-STAMB2-v1

This model was trained using BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts.

IMPORTANT NOTE:

This model was introduced in 2022. Since then, a new version has been published.
For most use cases, you will be better served by BioLORD-2023 , our latest generation of BioLORD models.

State-of-the-art methodologies operate by maximizing the similarity in representation of names referring to the same concept, and preventing collapse through contrastive learning. However, because biomedical names are not always self-explanatory, it sometimes results in non-semantic representations.

BioLORD overcomes this issue by grounding its concept representations using definitions, as well as short descriptions derived from a multi-relational knowledge graph consisting of biomedical ontologies. Thanks to this grounding, our model produces more semantic concept representations that match more closely the hierarchical structure of ontologies. BioLORD establishes a new state of the art for text similarity on both clinical sentences (MedSTS) and biomedical concepts (MayoSRS).

This model is based on sentence-transformers/all-mpnet-base-v2 and was further finetuned on the BioLORD-Dataset .

General purpose

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 model has been finentuned for the biomedical domain. While it preserves a good ability to produce embeddings for general-purpose text, it will be more useful to you if you are trying to process medical documents such as EHR records or clinical notes. Both sentences and phrases can be embedded in the same latent space.

Citation

This model accompanies the BioLORD: Learning Ontological Representations from Definitions paper, accepted in the EMNLP 2022 Findings. When you use this model, please cite the original paper as follows:

@inproceedings{remy-etal-2022-biolord,
    title = "{B}io{LORD}: Learning Ontological Representations from Definitions for Biomedical Concepts and their Textual Descriptions",
    author = "Remy, François  and
      Demuynck, Kris  and
      Demeester, Thomas",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-emnlp.104",
    pages = "1454--1465",
    abstract = "This work introduces BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts. State-of-the-art methodologies operate by maximizing the similarity in representation of names referring to the same concept, and preventing collapse through contrastive learning. However, because biomedical names are not always self-explanatory, it sometimes results in non-semantic representations. BioLORD overcomes this issue by grounding its concept representations using definitions, as well as short descriptions derived from a multi-relational knowledge graph consisting of biomedical ontologies. Thanks to this grounding, our model produces more semantic concept representations that match more closely the hierarchical structure of ontologies. BioLORD establishes a new state of the art for text similarity on both clinical sentences (MedSTS) and biomedical concepts (MayoSRS).",
}

You might also want to take a look at our MWE 2023 Paper:

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 = ["Cat scratch injury", "Cat scratch disease", "Bartonellosis"]

model = SentenceTransformer('FremyCompany/BioLORD-STAMB2-v1')
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
import torch.nn.functional as F

#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 = ["Cat scratch injury", "Cat scratch disease", "Bartonellosis"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('FremyCompany/BioLORD-STAMB2-v1')
model = AutoModel.from_pretrained('FremyCompany/BioLORD-STAMB2-v1')

# 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
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
License

My own contributions for this model are covered by the MIT license. However, given the data used to train this model originates from UMLS, you will need to ensure you have proper licensing of UMLS before using this model. UMLS is free of charge in most countries, but you might have to create an account and report on your usage of the data yearly to keep a valid license.

Runs of FremyCompany BioLORD-STAMB2-v1 on huggingface.co

75
Total runs
0
24-hour runs
-549
3-day runs
-516
7-day runs
-612
30-day runs

More Information About BioLORD-STAMB2-v1 huggingface.co Model

More BioLORD-STAMB2-v1 license Visit here:

https://choosealicense.com/licenses/other

BioLORD-STAMB2-v1 huggingface.co

BioLORD-STAMB2-v1 huggingface.co is an AI model on huggingface.co that provides BioLORD-STAMB2-v1's model effect (), which can be used instantly with this FremyCompany BioLORD-STAMB2-v1 model. huggingface.co supports a free trial of the BioLORD-STAMB2-v1 model, and also provides paid use of the BioLORD-STAMB2-v1. Support call BioLORD-STAMB2-v1 model through api, including Node.js, Python, http.

FremyCompany BioLORD-STAMB2-v1 online free

BioLORD-STAMB2-v1 huggingface.co is an online trial and call api platform, which integrates BioLORD-STAMB2-v1's modeling effects, including api services, and provides a free online trial of BioLORD-STAMB2-v1, you can try BioLORD-STAMB2-v1 online for free by clicking the link below.

FremyCompany BioLORD-STAMB2-v1 online free url in huggingface.co:

https://huggingface.co/FremyCompany/BioLORD-STAMB2-v1

BioLORD-STAMB2-v1 install

BioLORD-STAMB2-v1 is an open source model from GitHub that offers a free installation service, and any user can find BioLORD-STAMB2-v1 on GitHub to install. At the same time, huggingface.co provides the effect of BioLORD-STAMB2-v1 install, users can directly use BioLORD-STAMB2-v1 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

BioLORD-STAMB2-v1 install url in huggingface.co:

https://huggingface.co/FremyCompany/BioLORD-STAMB2-v1

Url of BioLORD-STAMB2-v1

BioLORD-STAMB2-v1 huggingface.co Url

Provider of BioLORD-STAMB2-v1 huggingface.co

FremyCompany
ORGANIZATIONS

Other API from FremyCompany