SCIENCE@home

PromptBERT: Improving BERT Sentence Embeddings with Prompts

Ting Jiang,Shaohan Huang,Zihan Zhang,Deqing Wang,Fuzhen Zhuang,Furu Wei,Haizhen Huang,Liangjie Zhang

Published 2022 in Conference on Empirical Methods in Natural Language Processing

ABSTRACT

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analysis 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.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-28 of 28 references · Page 1 of 1

CITED BY

Showing 1-100 of 153 citing papers · Page 1 of 2

12
Next