Python SimCSE Resources

SimCSE复现 项目描述 SimCSE是一种简单但是很巧妙的NLP对比学习方法，创新性地引入Dropout的方式，对样本添加噪声，从而达到对正样本增强的目的。 该框架的训练目的为：对于batch中的每个样本，拉近其与正样本之间的距离，拉远其与负样本之间的距离，使得模型能够在大规模无监督语料（也可以

Korean-Sentence-Embedding 🍭 Korean sentence embedding repository. You can download the pre-trained models and inference right away, also it provides

rapidnlp-datasets Data pipelines for both TensorFlow and PyTorch ! If you want to load public datasets, try: tensorflow/datasets huggingface/datasets

A PyTorch implementation of unsupervised SimCSE

SimCSE: Simple Contrastive Learning of Sentence Embeddings This repository contains the code and pre-trained models for our paper SimCSE: Simple Contr

KoSimCSE Korean Simple Contrastive Learning of Sentence Embeddings implementation using pytorch SimCSE Installation git clone https://github.com/BM-K/

KR-BERT-SimCSE Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT. Training Unsupervised python train_unsupervised.py --mi

SimCSE 中文测试 SimCSE在常见中文数据集上的测试，包含ATEC、BQ、LCQMC、PAWSX、STS-B共5个任务。 介绍 博客：https://kexue.fm/archives/8348 论文：《SimCSE: Simple Contrastive Learning of Sente

SimCSE: Simple Contrastive Learning of Sentence Embeddings This repository contains the code and pre-trained models for our paper SimCSE: Simple Contr