@inproceedings{tang-etal-2022-dptdr,
title = "{DPTDR}: Deep Prompt Tuning for Dense Passage Retrieval",
author = "Tang, Zhengyang and
Wang, Benyou and
Yao, Ting",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.103",
pages = "1193--1202",
abstract = "Deep prompt tuning (DPT) has gained great success in most natural language processing (NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning (FT) still dominates. When deploying multiple retrieval tasks using the same backbone model (e.g., RoBERTa), FT-based methods are unfriendly in terms of deployment cost: each new retrieval model needs to repeatedly deploy the backbone model without reuse. To reduce the deployment cost in such a scenario, this work investigates applying DPT in dense retrieval. The challenge is that directly applying DPT in dense retrieval largely underperforms FT methods. To compensate for the performance drop, we propose two model-agnostic and task-agnostic strategies for DPT-based retrievers, namely retrieval-oriented intermediate pretraining and unified negative mining, as a general approach that could be compatible with any pre-trained language model and retrieval task. The experimental results show that the proposed method (called DPTDR) outperforms previous state-of-the-art models on both MS-MARCO and Natural Questions. We also conduct ablation studies to examine the effectiveness of each strategy in DPTDR. We believe this work facilitates the industry, as it saves enormous efforts and costs of deployment and increases the utility of computing resources. Our code is available at \url{https://github.com/tangzhy/DPTDR}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2022-dptdr">
<titleInfo>
<title>DPTDR: Deep Prompt Tuning for Dense Passage Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhengyang</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benyou</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep prompt tuning (DPT) has gained great success in most natural language processing (NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning (FT) still dominates. When deploying multiple retrieval tasks using the same backbone model (e.g., RoBERTa), FT-based methods are unfriendly in terms of deployment cost: each new retrieval model needs to repeatedly deploy the backbone model without reuse. To reduce the deployment cost in such a scenario, this work investigates applying DPT in dense retrieval. The challenge is that directly applying DPT in dense retrieval largely underperforms FT methods. To compensate for the performance drop, we propose two model-agnostic and task-agnostic strategies for DPT-based retrievers, namely retrieval-oriented intermediate pretraining and unified negative mining, as a general approach that could be compatible with any pre-trained language model and retrieval task. The experimental results show that the proposed method (called DPTDR) outperforms previous state-of-the-art models on both MS-MARCO and Natural Questions. We also conduct ablation studies to examine the effectiveness of each strategy in DPTDR. We believe this work facilitates the industry, as it saves enormous efforts and costs of deployment and increases the utility of computing resources. Our code is available at https://github.com/tangzhy/DPTDR.</abstract>
<identifier type="citekey">tang-etal-2022-dptdr</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.103</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>1193</start>
<end>1202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DPTDR: Deep Prompt Tuning for Dense Passage Retrieval
%A Tang, Zhengyang
%A Wang, Benyou
%A Yao, Ting
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F tang-etal-2022-dptdr
%X Deep prompt tuning (DPT) has gained great success in most natural language processing (NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning (FT) still dominates. When deploying multiple retrieval tasks using the same backbone model (e.g., RoBERTa), FT-based methods are unfriendly in terms of deployment cost: each new retrieval model needs to repeatedly deploy the backbone model without reuse. To reduce the deployment cost in such a scenario, this work investigates applying DPT in dense retrieval. The challenge is that directly applying DPT in dense retrieval largely underperforms FT methods. To compensate for the performance drop, we propose two model-agnostic and task-agnostic strategies for DPT-based retrievers, namely retrieval-oriented intermediate pretraining and unified negative mining, as a general approach that could be compatible with any pre-trained language model and retrieval task. The experimental results show that the proposed method (called DPTDR) outperforms previous state-of-the-art models on both MS-MARCO and Natural Questions. We also conduct ablation studies to examine the effectiveness of each strategy in DPTDR. We believe this work facilitates the industry, as it saves enormous efforts and costs of deployment and increases the utility of computing resources. Our code is available at https://github.com/tangzhy/DPTDR.
%U https://aclanthology.org/2022.coling-1.103
%P 1193-1202
Markdown (Informal)
[DPTDR: Deep Prompt Tuning for Dense Passage Retrieval](https://aclanthology.org/2022.coling-1.103) (Tang et al., COLING 2022)
ACL
- Zhengyang Tang, Benyou Wang, and Ting Yao. 2022. DPTDR: Deep Prompt Tuning for Dense Passage Retrieval. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1193–1202, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.