metadata

extra_gated_heading: Access aimped/nlp-health-translation-base-en-de on Hugging Face
extra_gated_description: >-
  This is a form to enable access to this model on Hugging Face after you have
  been granted access from the Aimped. Please visit the [Aimped
  website](https://aimped.ai/) to Sign Up and accept our Terms of Use and
  Privacy Policy before submitting this form. Requests will be processed in 1-2
  days.
extra_gated_prompt: >-
  **Your Hugging Face account email address MUST match the email you provide on
  the Aimped website or your request will not be approved.**
extra_gated_button_content: Submit
extra_gated_fields:
  I agree to share my name, email address, and username with Aimped and confirm that I have already been granted download access on the Aimped website: checkbox
license: cc-by-nc-4.0
language:
  - en
  - de
metrics:
  - bleu
pipeline_tag: translation
widget:
  - text: >-
      Furthermore, histologic changes after surgical procedures which are
      performed in severe cases of corneal ectasia such as corneal crosslinking
      and penetrating keratoplasty (pKPL) as well as refractive surgical
      procedures which may lead to postsurgical ectasia are presented.
  - text: >-
      Approximately 75% of cases are asymptomatic; mild symptoms which can occur
      include sore throat and fever; in a proportion of cases more severe
      symptoms develop such as headache, neck stiffness, and paresthesia.
tags:
  - medical
  - translation
  - medical translation
datasets:
  - aimped/medical-translation-test-set

aimped logo

Description of the Model

Paper: arxiv.org/abs/2407.12126

The Medical Translation AI model represents a specialized language model, trained for the accurate translations of medical documents from English to German. Its primary objective is to provide healthcare professionals, researchers, and individuals within the medical field with a reliable tool for the precise translation of a wide spectrum of medical documents.

The development of this model entailed the utilization of the Hensinki/MarianMT neural translation architecture, which required 2+ days of intensive training using A100 (24G RAM) GPU. To create an exceptionally high-quality corpus for training the translation model, we combined both publicly available and proprietary datasets. These datasets were further enriched by meticulously curated text collected from online sources. In addition, the inclusion of clinical and discharge reports from diverse healthcare institutions enhanced the dataset's depth and diversity. This meticulous curation process plays a pivotal role in ensuring the model's ability to generate accurate translations tailored specifically to the medical domain, meeting the stringent standards expected by our users.

The versatility of the Medical Translation AI model extends to the translation of a wide array of healthcare-related documents, encompassing medical reports, patient records, medication instructions, research manuscripts, clinical trial documents, and more. By harnessing the capabilities of this model, users can efficiently and dependably obtain translations, thereby streamlining and expediting the often complex task of language translation within the medical field.

The model we have developed outperforms leading translation companies like Google, Helsinki-Opus/MarianMT, and DeepL when compared against our meticulously curated proprietary test data set.

	ROUGE	BLEU	METEOR	BERT
Aimped	0.77	0.56	0.75	0.93
Google	0.74	0.53	0.73	0.92
DeepL	0.74	0.50	0.72	0.92
Opus/MarianMT	0.63	0.37	0.62	0.88

Why should you use Aimped API?

To get started, you can easily use our open-source version of the models for research purposes. However, the models provided through the Aimped API are trained on new data every three months. This ensures that the models understand ongoing healthcare developments in the world and can identify the most relevant medical terminology without a knowledge cutoff. In addition, we implement post/pre processing steps to improve the translation quality. Naturally, our quality control ensures that the models' performance always remains at least similar to previous versions.

Text Format Requirements: The text to be translated must adhere to a structured and grammatically correct format, including proper paragraph and sentence structures. Spelling errors or formatting issues, such as line breaks occurring before the completion of a sentence, will not be automatically corrected.

How to Use:

To get the right results, use this function.

Install requirements

!pip install transformers
!pip install sentencepiece
!pip install aimped
import nltk
nltk.download('punkt')

import libraries

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
from aimped.nlp.translation import text_translate
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"

load model

model_path = "aimped/nlp-health-translation-base-en-de"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForSeq2SeqLM.from_pretrained(model_path)

translater = pipeline(
                        task="translation_en_to_de",
                        model=model,
                        tokenizer=tokenizer,
                        device= device,  
                        max_length=512,
                        num_beams=7,
                        early_stopping=False,
                        num_return_sequences=1,
                        do_sample=False,

                    )

Use Model:

sentence = "Kadeem Vicente comes in today for a follow-up office visit. The patient was seen by me approximately one month ago as a new patient and whose primary medical concerns a history of coronary artery disease."
translated_text = text_translate([sentence],source_lang="en", pipeline=translater)

Test Set

Trainin data: Public and in-house datasets.

Test data: Public and in-house datasets which is available here.