@inproceedings{yu-etal-2022-coco,
title = "{COCO}-{DR}: Combating Distribution Shift in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning",
author = "Yu, Yue and
Xiong, Chenyan and
Sun, Si and
Zhang, Chao and
Overwijk, Arnold",
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.95",
doi = "10.18653/v1/2022.emnlp-main.95",
pages = "1462--1479",
abstract = "We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the generalization ability of dense retrieval by combating the distribution shifts between source training tasks and target scenarios. To mitigate the impact of document differences, COCO-DR continues pretraining the language model on the target corpora to adapt the model to target distributions via COtinuous COtrastive learning. To prepare for unseen target queries, COCO-DR leverages implicit Distributionally Robust Optimization (iDRO) to reweight samples from different source query clusters for improving model robustness over rare queries during fine-tuning. COCO-DR achieves superior average performance on BEIR, the zero-shot retrieval benchmark. At BERT{\_}Base scale, COCO-DR Base outperforms other ZeroDR models with 60x larger size. At BERT{\_}Large scale, COCO-DR Large outperforms the giant GPT-3 embedding model which has 500x more parameters. Our analysis shows the correlation between COCO-DR{'}s effectiveness in combating distribution shifts and improving zero-shot accuracy. Our code and model can be found at \url{https://github.com/OpenMatch/COCO-DR}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2022-coco">
<titleInfo>
<title>COCO-DR: Combating Distribution Shift in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyan</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnold</namePart>
<namePart type="family">Overwijk</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>We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the generalization ability of dense retrieval by combating the distribution shifts between source training tasks and target scenarios. To mitigate the impact of document differences, COCO-DR continues pretraining the language model on the target corpora to adapt the model to target distributions via COtinuous COtrastive learning. To prepare for unseen target queries, COCO-DR leverages implicit Distributionally Robust Optimization (iDRO) to reweight samples from different source query clusters for improving model robustness over rare queries during fine-tuning. COCO-DR achieves superior average performance on BEIR, the zero-shot retrieval benchmark. At BERT_Base scale, COCO-DR Base outperforms other ZeroDR models with 60x larger size. At BERT_Large scale, COCO-DR Large outperforms the giant GPT-3 embedding model which has 500x more parameters. Our analysis shows the correlation between COCO-DR’s effectiveness in combating distribution shifts and improving zero-shot accuracy. Our code and model can be found at https://github.com/OpenMatch/COCO-DR.</abstract>
<identifier type="citekey">yu-etal-2022-coco</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.95</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.95</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1462</start>
<end>1479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COCO-DR: Combating Distribution Shift in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning
%A Yu, Yue
%A Xiong, Chenyan
%A Sun, Si
%A Zhang, Chao
%A Overwijk, Arnold
%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 yu-etal-2022-coco
%X We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the generalization ability of dense retrieval by combating the distribution shifts between source training tasks and target scenarios. To mitigate the impact of document differences, COCO-DR continues pretraining the language model on the target corpora to adapt the model to target distributions via COtinuous COtrastive learning. To prepare for unseen target queries, COCO-DR leverages implicit Distributionally Robust Optimization (iDRO) to reweight samples from different source query clusters for improving model robustness over rare queries during fine-tuning. COCO-DR achieves superior average performance on BEIR, the zero-shot retrieval benchmark. At BERT_Base scale, COCO-DR Base outperforms other ZeroDR models with 60x larger size. At BERT_Large scale, COCO-DR Large outperforms the giant GPT-3 embedding model which has 500x more parameters. Our analysis shows the correlation between COCO-DR’s effectiveness in combating distribution shifts and improving zero-shot accuracy. Our code and model can be found at https://github.com/OpenMatch/COCO-DR.
%R 10.18653/v1/2022.emnlp-main.95
%U https://aclanthology.org/2022.emnlp-main.95
%U https://doi.org/10.18653/v1/2022.emnlp-main.95
%P 1462-1479
Markdown (Informal)
[COCO-DR: Combating Distribution Shift in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning](https://aclanthology.org/2022.emnlp-main.95) (Yu et al., EMNLP 2022)
ACL