@inproceedings{jiang-etal-2022-promptbert,
title = "{P}rompt{BERT}: Improving {BERT} Sentence Embeddings with Prompts",
author = "Jiang, Ting and
Jiao, Jian and
Huang, Shaohan and
Zhang, Zihan and
Wang, Deqing and
Zhuang, Fuzhen and
Wei, Furu and
Huang, Haizhen and
Deng, Denvy and
Zhang, Qi",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.603",
doi = "10.18653/v1/2022.emnlp-main.603",
pages = "8826--8837",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2022-promptbert">
<titleInfo>
<title>PromptBERT: Improving BERT Sentence Embeddings with Prompts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaohan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuzhen</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haizhen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denvy</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">jiang-etal-2022-promptbert</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.603</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.603</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>8826</start>
<end>8837</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PromptBERT: Improving BERT Sentence Embeddings with Prompts
%A Jiang, Ting
%A Jiao, Jian
%A Huang, Shaohan
%A Zhang, Zihan
%A Wang, Deqing
%A Zhuang, Fuzhen
%A Wei, Furu
%A Huang, Haizhen
%A Deng, Denvy
%A Zhang, Qi
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F jiang-etal-2022-promptbert
%X 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.
%R 10.18653/v1/2022.emnlp-main.603
%U https://aclanthology.org/2022.emnlp-main.603
%U https://doi.org/10.18653/v1/2022.emnlp-main.603
%P 8826-8837
Markdown (Informal)
[PromptBERT: Improving BERT Sentence Embeddings with Prompts](https://aclanthology.org/2022.emnlp-main.603) (Jiang et al., EMNLP 2022)
ACL
- Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, and Qi Zhang. 2022. PromptBERT: Improving BERT Sentence Embeddings with Prompts. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8826–8837, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.