@inproceedings{liu-etal-2021-quadrupletbert,
title = "{Q}uadruplet{BERT}: An Efficient Model For Embedding-Based Large-Scale Retrieval",
author = "Liu, Peiyang and
Wang, Sen and
Wang, Xi and
Ye, Wei and
Zhang, Shikun",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.292",
doi = "10.18653/v1/2021.naacl-main.292",
pages = "3734--3739",
abstract = "The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field. Considering that pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, we present a QuadrupletBERT model for effective and efficient retrieval in this paper. Unlike most existing BERT-style retrieval models, which only focus on the ranking phase in retrieval systems, our model makes considerable improvements to the retrieval phase and leverages the distances between simple negative and hard negative instances to obtaining better embeddings. Experimental results demonstrate that our QuadrupletBERT achieves state-of-the-art results in embedding-based large-scale retrieval tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-quadrupletbert">
<titleInfo>
<title>QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peiyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field. Considering that pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, we present a QuadrupletBERT model for effective and efficient retrieval in this paper. Unlike most existing BERT-style retrieval models, which only focus on the ranking phase in retrieval systems, our model makes considerable improvements to the retrieval phase and leverages the distances between simple negative and hard negative instances to obtaining better embeddings. Experimental results demonstrate that our QuadrupletBERT achieves state-of-the-art results in embedding-based large-scale retrieval tasks.</abstract>
<identifier type="citekey">liu-etal-2021-quadrupletbert</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.292</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.292</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3734</start>
<end>3739</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval
%A Liu, Peiyang
%A Wang, Sen
%A Wang, Xi
%A Ye, Wei
%A Zhang, Shikun
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F liu-etal-2021-quadrupletbert
%X The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field. Considering that pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, we present a QuadrupletBERT model for effective and efficient retrieval in this paper. Unlike most existing BERT-style retrieval models, which only focus on the ranking phase in retrieval systems, our model makes considerable improvements to the retrieval phase and leverages the distances between simple negative and hard negative instances to obtaining better embeddings. Experimental results demonstrate that our QuadrupletBERT achieves state-of-the-art results in embedding-based large-scale retrieval tasks.
%R 10.18653/v1/2021.naacl-main.292
%U https://aclanthology.org/2021.naacl-main.292
%U https://doi.org/10.18653/v1/2021.naacl-main.292
%P 3734-3739
Markdown (Informal)
[QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval](https://aclanthology.org/2021.naacl-main.292) (Liu et al., NAACL 2021)
ACL