https://github.com/sense-gvt/sncse
공식 코드SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples
Clustering and Network Analysis for the Embedding Spaces of Sentences and Sub-Sentences
Some Like It Small: Czech Semantic Embedding Models for Industry Applications
Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representations
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder
EASE: Entity-Aware Contrastive Learning of Sentence Embedding
DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks
TagGPT: Large Language Models are Zero-shot Multimodal Taggers
Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models
MCSE: Multimodal Contrastive Learning of Sentence Embeddings
AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification
Global Contrastive Batch Sampling via Optimization on Sample Permutations
Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding
An Unsupervised Sentence Embedding Method by Mutual Information Maximization
English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings
Ranking-Enhanced Unsupervised Sentence Representation Learning
Sentence-level Media Bias Analysis with Event Relation Graph
Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
Improving One-stage Visual Grounding by Recursive Sub-query Construction
DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.