Medical mT5: An Open-Source Multilingual Text-to-Text LLM for the Medical Domain
Model Card for Medical MT5-xl-multitask
Medical MT5-xl-multitask is a version of Medical MT5 finetuned for sequence labelling. It can correctly label a wide range of Medical labels in unstructured text, such as Disease
, Disability
, ClinicalEntity
, Chemical
... Medical MT5-xl-multitask has been finetuned for English, Spanish, French and Italian, although it may work with a wide range of languages.
- 📖 Paper: Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain
- 🌐 Project Website: https://univ-cotedazur.eu/antidote
Open Source Models
HiTZ/Medical-mT5-large | HiTZ/Medical-MT5-xl | HiTZ/Medical-mT5-large-multitask | HiTZ/Medical-MT5-xl-multitask | |
---|---|---|---|---|
Param. no. | 738M | 3B | 738M | 3B |
Task | Language Modeling | Language Modeling | Multitask Sequence Labeling | Multitask Sequence Labeling |
Usage
Medical MT5-xl-multitask was training using the Sequence-Labeling-LLMs library: https://github.com/ikergarcia1996/Sequence-Labeling-LLMs/
This library uses constrained decoding to ensure that the output contains the same words as the input and a valid HTML annotation. We recommend using Medical MT5-xl-multitask together with this library.
Although you can also directly use it with 🤗 huggingface. In order to label a sentence, you need to append the labels you wan to use, for example, if you want to label dieseases you should format your input as follows: <Disease> Torsade de pointes ventricular tachycardia during low dose intermittent dobutamine treatment in a patient with dilated cardiomyopathy and congestive heart failure .
import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model = AutoModelForSeq2SeqLM.from_pretrained("Medical-MT5-xl-multitask",torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("Medical-MT5-xl-multitask")
input_example = "<Disease> Torsade de pointes ventricular tachycardia during low dose intermittent dobutamine treatment in a patient with dilated cardiomyopathy and congestive heart failure ."
model_input = tokenizer(input_example, return_tensors="pt")
output = model.generate(**model_input.to(model.device),max_new_tokens=128,num_beams=1,num_return_sequences=1,do_sample=False)
print(tokenizer.decode(output[0], skip_special_tokens=True))
Performance
![](https://raw.githubusercontent.com/ikergarcia1996/Sequence-Labeling-LLMs/main/resources/multitask_performance.png)
Model Description
- Developed by: Iker García-Ferrero, Rodrigo Agerri, Aitziber Atutxa Salazar, Elena Cabrio, Iker de la Iglesia, Alberto Lavelli, Bernardo Magnini, Benjamin Molinet, Johana Ramirez-Romero, German Rigau, Jose Maria Villa-Gonzalez, Serena Villata and Andrea Zaninello
- Contact: Iker García-Ferrero and Rodrigo Agerri
- Website: https://univ-cotedazur.eu/antidote
- Funding: CHIST-ERA XAI 2019 call. Antidote (PCI2020-120717-2) funded by MCIN/AEI /10.13039/501100011033 and by European Union NextGenerationEU/PRTR
- Model type: text2text-generation
- Language(s) (NLP): English, Spanish, French, Italian
- License: apache-2.0
- Finetuned from model: HiTZ/Medical-MT5-xl
Ethical Statement
Our research in developing Medical mT5, a multilingual text-to-text model for the medical domain, has ethical implications that we acknowledge. Firstly, the broader impact of this work lies in its potential to improve medical communication and understanding across languages, which can enhance healthcare access and quality for diverse linguistic communities. However, it also raises ethical considerations related to privacy and data security. To create our multilingual corpus, we have taken measures to anonymize and protect sensitive patient information, adhering to data protection regulations in each language's jurisdiction or deriving our data from sources that explicitly address this issue in line with privacy and safety regulations and guidelines. Furthermore, we are committed to transparency and fairness in our model's development and evaluation. We have worked to ensure that our benchmarks are representative and unbiased, and we will continue to monitor and address any potential biases in the future. Finally, we emphasize our commitment to open source by making our data, code, and models publicly available, with the aim of promoting collaboration within the research community.
Citation
@misc{garcíaferrero2024medical,
title={Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain},
author={Iker García-Ferrero and Rodrigo Agerri and Aitziber Atutxa Salazar and Elena Cabrio and Iker de la Iglesia and Alberto Lavelli and Bernardo Magnini and Benjamin Molinet and Johana Ramirez-Romero and German Rigau and Jose Maria Villa-Gonzalez and Serena Villata and Andrea Zaninello},
year={2024},
eprint={2404.07613},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- Downloads last month
- 5