DiffCSE

Sentence embedder

An unsupervised contrastive learning framework for learning sentence embeddings sensitive to differences between original and edited sentences.

Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"

GitHub

292 stars
4 watching
27 forks
Language: Python
last commit: almost 4 years ago
contrastive-learningrepresentation-learningself-supervised-learningsentence-embeddingssentence-similaritysentence-transformers

Related projects:

RepositoryDescriptionStars
johngiorgi/declutrA tool for training and evaluating sentence embeddings using deep contrastive learning380
kostyaev/sentence2vecThis is a tool for creating deep sentence embeddings using Sequence-to-Sequence learning.22
tca19/dict2vecA framework to learn word embeddings using lexical dictionaries115
xiaoqijiao/coling2018Provides training and testing code for a CNN-based sentence embedding model2
epfml/sent2vecAn unsupervised technique to generate numerical representations of sentences and words for use in machine learning tasks1,194
auspicious3000/contentvecAn implementation of a self-supervised speech representation model using PyTorch and disentangled speaker embeddings471
lajanugen/s2vAn implementation of a neural network model for learning efficient sentence representations from text data.205
iarroyof/sentence_embeddingA method to convert word embeddings into sentence representations by applying entropy weights calculated from TFIDF transform.9
jwieting/iclr2016Code for training universal paraphrastic sentence embeddings and models on semantic similarity tasks193
fursovia/geometric_embeddingAn implementation of a non-parameterized approach for building sentence representations19
binwang28/sbert-wk-sentence-embeddingA method to generate sentence embeddings from pre-trained language models178
jwieting/acl2017A codebase for training and using models of sentence embeddings.33
benedekrozemberczki/diff2vecA reference implementation of Diffusion2Vec, a method for learning node embeddings from graph data.128
fh295/sentencerepresentationA software framework for learning sentence representations using unsupervised machine learning algorithms124
benedekrozemberczki/teneA sparsity-aware implementation of a deep learning algorithm for graph embedding with text information.74