@inproceedings{zerveas-etal-2022-coder,
title = "{CODER}: An efficient framework for improving retrieval through {CO}ntextual Document Embedding Reranking",
author = "Zerveas, George and
Rekabsaz, Navid and
Cohen, Daniel and
Eickhoff, Carsten",
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.727",
doi = "10.18653/v1/2022.emnlp-main.727",
pages = "10626--10644",
abstract = "Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine the effect of its constituent parts: jointly scoring a large number of negatives per query, using retrieved (query-specific) instead of random negatives, and a fully list-wise loss. To incorporate these factors into training, we introduce Contextual Document Embedding Reranking (CODER), a highly efficient retrieval framework. When reranking, it incurs only a negligible computational overhead on top of a first-stage method at run time (approx. 5 ms delay per query), allowing it to be easily combined with any state-of-the-art dual encoder method. Models trained through CODER can also be used as stand-alone retrievers. Evaluating CODER in a large set of experiments on the MS MARCO and TripClick collections, we show that the contextual reranking of precomputed document embeddings leads to a significant improvement in retrieval performance. This improvement becomes even more pronounced when more relevance information per query is available, shown in the TripClick collection, where we establish new state-of-the-art results by a large margin.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zerveas-etal-2022-coder">
<titleInfo>
<title>CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Zerveas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navid</namePart>
<namePart type="family">Rekabsaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carsten</namePart>
<namePart type="family">Eickhoff</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>Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine the effect of its constituent parts: jointly scoring a large number of negatives per query, using retrieved (query-specific) instead of random negatives, and a fully list-wise loss. To incorporate these factors into training, we introduce Contextual Document Embedding Reranking (CODER), a highly efficient retrieval framework. When reranking, it incurs only a negligible computational overhead on top of a first-stage method at run time (approx. 5 ms delay per query), allowing it to be easily combined with any state-of-the-art dual encoder method. Models trained through CODER can also be used as stand-alone retrievers. Evaluating CODER in a large set of experiments on the MS MARCO and TripClick collections, we show that the contextual reranking of precomputed document embeddings leads to a significant improvement in retrieval performance. This improvement becomes even more pronounced when more relevance information per query is available, shown in the TripClick collection, where we establish new state-of-the-art results by a large margin.</abstract>
<identifier type="citekey">zerveas-etal-2022-coder</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.727</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.727</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>10626</start>
<end>10644</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking
%A Zerveas, George
%A Rekabsaz, Navid
%A Cohen, Daniel
%A Eickhoff, Carsten
%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 zerveas-etal-2022-coder
%X Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine the effect of its constituent parts: jointly scoring a large number of negatives per query, using retrieved (query-specific) instead of random negatives, and a fully list-wise loss. To incorporate these factors into training, we introduce Contextual Document Embedding Reranking (CODER), a highly efficient retrieval framework. When reranking, it incurs only a negligible computational overhead on top of a first-stage method at run time (approx. 5 ms delay per query), allowing it to be easily combined with any state-of-the-art dual encoder method. Models trained through CODER can also be used as stand-alone retrievers. Evaluating CODER in a large set of experiments on the MS MARCO and TripClick collections, we show that the contextual reranking of precomputed document embeddings leads to a significant improvement in retrieval performance. This improvement becomes even more pronounced when more relevance information per query is available, shown in the TripClick collection, where we establish new state-of-the-art results by a large margin.
%R 10.18653/v1/2022.emnlp-main.727
%U https://aclanthology.org/2022.emnlp-main.727
%U https://doi.org/10.18653/v1/2022.emnlp-main.727
%P 10626-10644
Markdown (Informal)
[CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking](https://aclanthology.org/2022.emnlp-main.727) (Zerveas et al., EMNLP 2022)
ACL