paper-with-me

홈 › Papers

PromptBERT: Improving BERT Sentence Embeddings with Prompts

2022-01-12 · Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang

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 the static token embedding bias and ineffective BERT layers. Then we propose the first prompt-based sentence embeddings method and discuss two prompt representing methods and three prompt searching methods to make BERT achieve better sentence embeddings. Moreover, we propose a novel unsupervised training objective by the technology of template denoising, which substantially shortens the performance gap between the supervised and unsupervised settings. Extensive experiments show the effectiveness of our method. Compared to SimCSE, PromptBert achieves 2.29 and 2.58 points of improvement based on BERT and RoBERTa in the unsupervised setting.

📄 PDF Abstract BibTeX arXiv:2201.04337

Code (1)

kongds/prompt-bert 공식 구현 pytorch

Tasks

Contrastive LearningDenoisingSemantic SimilaritySemantic Textual SimilaritySentenceSentence EmbeddingSentence-EmbeddingSentence EmbeddingsSTS

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Contrastive Learning 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
WordPiece 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

PromptBERT: Improving BERT Sentence Embeddings with Prompts

2021-11-16 · ACL ARR November 2021 11 · Anonymous

The poor performance of the original BERT for sentence semantic similarity has been widely discussed in previous works. We find that unsatisfactory performance is mainly due to the static token embeddings biases and th…

DenoisingSemantic SimilaritySemantic Textual SimilaritySentence+2

AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback

2025-01-23 · Joshua Park, Yongfeng Zhang

Multi-agent systems must decide which agent is the most appropriate for a given task. We propose a novel architecture for recommending which LLM agent out of many should perform a task given a natural language prompt by …

reinforcement-learningReinforcement LearningSentenceSentence Embeddings

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-trai…

Contrastive LearningLanguage ModelingLanguage ModellingSentence+1

Dual-View Distilled BERT for Sentence Embedding

2021-04-18 · Xingyi Cheng

Recently, BERT realized significant progress for sentence matching via word-level cross sentence attention. However, the performance significantly drops when using siamese BERT-networks to derive two sentence embeddings,…

SentenceSentence EmbeddingSentence-EmbeddingSentence Embeddings+1

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

2019-08-27 · IJCNLP 2019 11 · Nils Reimers, Iryna Gurevych

BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are …

ClusteringLinear-Probe ClassificationSemantic SimilaritySemantic Textual Similarity+6