@inproceedings{chen-etal-2022-salient,
title = "Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?",
author = "Chen, Xilun and
Lakhotia, Kushal and
Oguz, Barlas and
Gupta, Anchit and
Lewis, Patrick and
Peshterliev, Stan and
Mehdad, Yashar and
Gupta, Sonal and
Yih, Wen-tau",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.19",
doi = "10.18653/v1/2022.findings-emnlp.19",
pages = "250--262",
abstract = "Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Λ. Empirically, SPAR shows superior performance on a range of tasks including five question answering datasets, MS MARCO passage retrieval, as well as the EntityQuestions and BEIR benchmarks for out-of-domain evaluation, exceeding the performance of state-of-the-art dense and sparse retrievers. The code and models of SPAR are available at: \url{https://github.com/facebookresearch/dpr-scale/tree/main/spar}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-salient">
<titleInfo>
<title>Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xilun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Lakhotia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barlas</namePart>
<namePart type="family">Oguz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anchit</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Peshterliev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yashar</namePart>
<namePart type="family">Mehdad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonal</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</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>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Λ. Empirically, SPAR shows superior performance on a range of tasks including five question answering datasets, MS MARCO passage retrieval, as well as the EntityQuestions and BEIR benchmarks for out-of-domain evaluation, exceeding the performance of state-of-the-art dense and sparse retrievers. The code and models of SPAR are available at: https://github.com/facebookresearch/dpr-scale/tree/main/spar</abstract>
<identifier type="citekey">chen-etal-2022-salient</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.19</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.19</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>250</start>
<end>262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
%A Chen, Xilun
%A Lakhotia, Kushal
%A Oguz, Barlas
%A Gupta, Anchit
%A Lewis, Patrick
%A Peshterliev, Stan
%A Mehdad, Yashar
%A Gupta, Sonal
%A Yih, Wen-tau
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F chen-etal-2022-salient
%X Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Λ. Empirically, SPAR shows superior performance on a range of tasks including five question answering datasets, MS MARCO passage retrieval, as well as the EntityQuestions and BEIR benchmarks for out-of-domain evaluation, exceeding the performance of state-of-the-art dense and sparse retrievers. The code and models of SPAR are available at: https://github.com/facebookresearch/dpr-scale/tree/main/spar
%R 10.18653/v1/2022.findings-emnlp.19
%U https://aclanthology.org/2022.findings-emnlp.19
%U https://doi.org/10.18653/v1/2022.findings-emnlp.19
%P 250-262
Markdown (Informal)
[Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?](https://aclanthology.org/2022.findings-emnlp.19) (Chen et al., Findings 2022)
ACL
- Xilun Chen, Kushal Lakhotia, Barlas Oguz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, and Wen-tau Yih. 2022. Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 250–262, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.