Open-source MiniLM-L6-v2 Model Dedicated to Clinical Research - Supports Tasks like Text Semantic Similarity Calculation

Clinical Trials All MiniLM L6 V2

Developed by Vinit3241

This is a fine-tuned sentence transformer model based on sentence-transformers/all-MiniLM-L6-v2, designed to map text into a 384-dimensional vector space, supporting tasks like semantic similarity computation.

Text Embedding

Safetensors

#Medical Text Similarity #Clinical Research Feature Extraction #Multi-Loss Joint Optimization

Downloads 49

Release Time : 1/25/2025

Model Overview

This model is specifically designed for vectorized representations of sentences and paragraphs, applicable to various natural language processing tasks such as semantic text similarity, semantic search, text classification, and clustering.

Model Features

Efficient Semantic Encoding

Efficiently encodes sentences and paragraphs into 384-dimensional dense vectors while preserving semantic information

Medical Domain Optimization

Specially optimized for medical texts, better handling professional medical terminology

Multiple Loss Functions

Utilizes a combination of Russian Doll Loss and Multiple Negative Ranking Loss for training

Model Capabilities

Semantic Text Similarity Computation

Semantic Search

Paraphrase Mining

Text Classification

Text Clustering

Use Cases

Medical Research

Clinical Trial Document Matching

Matching similar clinical trial descriptions to assist research design

Medical Literature Retrieval

Semantic-based medical literature retrieval system

Biomedicine

Drug Research Document Analysis

Analyzing similarity in drug research documents

🚀 Sentence Transformers for Similarity and Feature Extraction

This project is based on sentence-transformers, aiming to perform tasks such as sentence similarity calculation and feature extraction. It uses specific loss functions and a base model to achieve high - performance results.

✨ Features

Multiple Loss Functions: Utilizes MatryoshkaLoss and MultipleNegativesRankingLoss for training.
Base Model: Built upon sentence-transformers/all-MiniLM-L6-v2.
Widget Demonstration: Allows users to input source sentences and compare them with a set of target sentences to check similarity.

📚 Documentation

Widget Usage

The widget provides a practical way to test the model's performance. You can input a source_sentence and a list of sentences to see how the model calculates similarity.

Example 1

source_sentence: aprepitant prevention chemotherapy induce nausea vomit cinv0869130complete.
The purpose of this study is to assess the efficacy and safety of recombinant
human tissue plasminogen kinase derivatives for injection and alteplase in the
treatment of patients with acute ischemic stroke within 4.5 hours.
sentences:
  - Coronary Artery Diseases|Multivessel Coronary Artery Disease|Heart Diseases|Cardiovascular
    Diseases inclusion criteria...
  - 'HIV Infections inclusion criterion...'
  - "Chemotherapy-Induced Nausea and Vomiting inclusion criterion..."

Example 2

source_sentence: eribulin mesylate phase iv clinical trial korean patient metastatic
locally advanced breast cancer. This study will treat patients with Metastatic
Castration Resistant Prostate Cancer who have progressed following prior therapy...
sentences:
  - End Stage Renal Disease inclusion criterion...
  - Skin Laxity inclusion criterion...
  - Breast Neoplasms|Breast Cancer inclusion criteria...

Example 3

source_sentence: 'safety study mt4666 subject alzheimer disease. This is a phase
1, randomized, open label, single - dose, replicate crossover clinical trial to
compare the safety and pharmacokinetics of YH22162 in healthy male volunteers...'
sentences:
  - Alzheimer's Disease inclusion criterion...
  - 'Type 2 Diabetes inclusion criteria...'

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご