paper-with-me

홈 › Papers

Deep Continuous Prompt for Contrastive Learning of Sentence Embeddings

2022-01-16 · ACL ARR January 2022 1 · Anonymous

The performance of sentence representation has been remarkably improved by the framework of contrastive learning. However, recent works still require full fine-tuning, which is quite inefficient for large-scaled pre-trained language models. To this end, we present a novel method which freezes the whole language model and only optimizes the prefix deep continuous prompts. It not only tunes around 0.1\% parameters of the original language model, but avoids the cumbersome computation of searching handcrafted prompts. Experimental results show that our proposed DCPCSE outperforms the state-of-the-art method SimCSE by a large margin. We raise the performance of unsupervised BERT$_{base}$ and supervised RoBERTa$_{large}$ by 2.24 and 1.00 points, respectively. Our code will be released at Github.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningLanguage ModelingLanguage ModellingSentenceSentence Embeddings

Methods 이 논문이 사용한 방법론

SimCSE SimCSE is a contrastive learning framework for generating sentence embeddings. It utilizes an unsupervised approach, which takes an input sentence and predicts itself in…

Similar Papers 제목 키워드 기반

D2CSE: Difference-aware Deep continuous prompts for Contrastive Sentence Embeddings

2023-04-18 · Hyunjae Lee

This paper describes Difference-aware Deep continuous prompt for Contrastive Sentence Embeddings (D2CSE) that learns sentence embeddings. Compared to state-of-the-art approaches, D2CSE computes sentence vectors that are …

Contrastive LearningRetrievalSemantic Textual SimilaritySentence+2

Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning

2022-03-14 · Yuxin Jiang, Linhan Zhang, Wei Wang

Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitation…

AttributeContrastive LearningSemantic Textual SimilaritySentence+2

PromptBERT: Improving BERT Sentence Embeddings with Prompts

2022-01-12 · Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang 외

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to t…

Contrastive LearningDenoisingSemantic SimilaritySemantic Textual Similarity+5

Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence Embedding

2022-11-07 · Jiali Zeng, Yongjing Yin, Yufan Jiang, Shuangzhi Wu 외

Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In…

ClusteringContrastive LearningData AugmentationSemantic Textual Similarity+4

Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering

2025-05-19 · Zifeng Cheng, Zhonghui Wang, Yuchen Fu, Zhiwei Jiang 외

Extracting sentence embeddings from large language models (LLMs) is a practical direction, as it requires neither additional data nor fine-tuning. Previous studies usually focus on prompt engineering to guide LLMs to enc…

Prompt EngineeringSemantic Textual SimilaritySentenceSentence Embedding+3