@inproceedings{kim-etal-2022-pseudo,
title = "Pseudo-Relevance for Enhancing Document Representation",
author = "Kim, Jihyuk and
Hwang, Seung-won and
Song, Seoho and
Ko, Hyeseon and
Song, Young-In",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
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.800",
doi = "10.18653/v1/2022.emnlp-main.800",
pages = "11639--11652",
abstract = "This paper studies how to enhance the document representation for the bi-encoder approach in dense document retrieval. The bi-encoder, separately encoding a query and a document as a single vector, is favored for high efficiency in large-scale information retrieval, compared to more effective but complex architectures. To combine the strength of the two, the multi-vector representation of documents for bi-encoder, such as ColBERT preserving all token embeddings, has been widely adopted. Our contribution is to reduce the size of the multi-vector representation, without compromising the effectiveness, supervised by query logs. Our proposed solution decreases the latency and the memory footprint, up to 8- and 3-fold, validated on MSMARCO and real-world search query logs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2022-pseudo">
<titleInfo>
<title>Pseudo-Relevance for Enhancing Document Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jihyuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seoho</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeseon</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Young-In</namePart>
<namePart type="family">Song</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>
<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>This paper studies how to enhance the document representation for the bi-encoder approach in dense document retrieval. The bi-encoder, separately encoding a query and a document as a single vector, is favored for high efficiency in large-scale information retrieval, compared to more effective but complex architectures. To combine the strength of the two, the multi-vector representation of documents for bi-encoder, such as ColBERT preserving all token embeddings, has been widely adopted. Our contribution is to reduce the size of the multi-vector representation, without compromising the effectiveness, supervised by query logs. Our proposed solution decreases the latency and the memory footprint, up to 8- and 3-fold, validated on MSMARCO and real-world search query logs.</abstract>
<identifier type="citekey">kim-etal-2022-pseudo</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.800</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.800</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11639</start>
<end>11652</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pseudo-Relevance for Enhancing Document Representation
%A Kim, Jihyuk
%A Hwang, Seung-won
%A Song, Seoho
%A Ko, Hyeseon
%A Song, Young-In
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%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 kim-etal-2022-pseudo
%X This paper studies how to enhance the document representation for the bi-encoder approach in dense document retrieval. The bi-encoder, separately encoding a query and a document as a single vector, is favored for high efficiency in large-scale information retrieval, compared to more effective but complex architectures. To combine the strength of the two, the multi-vector representation of documents for bi-encoder, such as ColBERT preserving all token embeddings, has been widely adopted. Our contribution is to reduce the size of the multi-vector representation, without compromising the effectiveness, supervised by query logs. Our proposed solution decreases the latency and the memory footprint, up to 8- and 3-fold, validated on MSMARCO and real-world search query logs.
%R 10.18653/v1/2022.emnlp-main.800
%U https://aclanthology.org/2022.emnlp-main.800
%U https://doi.org/10.18653/v1/2022.emnlp-main.800
%P 11639-11652
Markdown (Informal)
[Pseudo-Relevance for Enhancing Document Representation](https://aclanthology.org/2022.emnlp-main.800) (Kim et al., EMNLP 2022)
ACL
- Jihyuk Kim, Seung-won Hwang, Seoho Song, Hyeseon Ko, and Young-In Song. 2022. Pseudo-Relevance for Enhancing Document Representation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11639–11652, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.