@inproceedings{qiu-etal-2022-dureader,
title = "{D}u{R}eader-Retrieval: A Large-scale {C}hinese Benchmark for Passage Retrieval from Web Search Engine",
author = "Qiu, Yifu and
Li, Hongyu and
Qu, Yingqi and
Chen, Ying and
She, QiaoQiao and
Liu, Jing and
Wu, Hua and
Wang, Haifeng",
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.357/",
doi = "10.18653/v1/2022.emnlp-main.357",
pages = "5326--5338",
abstract = "In this paper, we present DuReader-retrieval, a large-scale Chinese dataset for passage retrieval. DuReader-retrieval contains more than 90K queries and over 8M unique passages from a commercial search engine. To alleviate the shortcomings of other datasets and ensure the quality of our benchmark, we (1) reduce the false negatives in development and test sets by manually annotating results pooled from multiple retrievers, and (2) remove the training queries that are semantically similar to the development and testing queries. Additionally, we provide two out-of-domain testing sets for cross-domain evaluation, as well as a set of human translated queries for for cross-lingual retrieval evaluation. The experiments demonstrate that DuReader-retrieval is challenging and a number of problems remain unsolved, such as the salient phrase mismatch and the syntactic mismatch between queries and paragraphs. These experiments also show that dense retrievers do not generalize well across domains, and cross-lingual retrieval is essentially challenging. DuReader-retrieval is publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-etal-2022-dureader">
<titleInfo>
<title>DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifu</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingqi</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">QiaoQiao</namePart>
<namePart type="family">She</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Wang</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>In this paper, we present DuReader-retrieval, a large-scale Chinese dataset for passage retrieval. DuReader-retrieval contains more than 90K queries and over 8M unique passages from a commercial search engine. To alleviate the shortcomings of other datasets and ensure the quality of our benchmark, we (1) reduce the false negatives in development and test sets by manually annotating results pooled from multiple retrievers, and (2) remove the training queries that are semantically similar to the development and testing queries. Additionally, we provide two out-of-domain testing sets for cross-domain evaluation, as well as a set of human translated queries for for cross-lingual retrieval evaluation. The experiments demonstrate that DuReader-retrieval is challenging and a number of problems remain unsolved, such as the salient phrase mismatch and the syntactic mismatch between queries and paragraphs. These experiments also show that dense retrievers do not generalize well across domains, and cross-lingual retrieval is essentially challenging. DuReader-retrieval is publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval.</abstract>
<identifier type="citekey">qiu-etal-2022-dureader</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.357</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.357/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5326</start>
<end>5338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine
%A Qiu, Yifu
%A Li, Hongyu
%A Qu, Yingqi
%A Chen, Ying
%A She, QiaoQiao
%A Liu, Jing
%A Wu, Hua
%A Wang, Haifeng
%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 qiu-etal-2022-dureader
%X In this paper, we present DuReader-retrieval, a large-scale Chinese dataset for passage retrieval. DuReader-retrieval contains more than 90K queries and over 8M unique passages from a commercial search engine. To alleviate the shortcomings of other datasets and ensure the quality of our benchmark, we (1) reduce the false negatives in development and test sets by manually annotating results pooled from multiple retrievers, and (2) remove the training queries that are semantically similar to the development and testing queries. Additionally, we provide two out-of-domain testing sets for cross-domain evaluation, as well as a set of human translated queries for for cross-lingual retrieval evaluation. The experiments demonstrate that DuReader-retrieval is challenging and a number of problems remain unsolved, such as the salient phrase mismatch and the syntactic mismatch between queries and paragraphs. These experiments also show that dense retrievers do not generalize well across domains, and cross-lingual retrieval is essentially challenging. DuReader-retrieval is publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval.
%R 10.18653/v1/2022.emnlp-main.357
%U https://aclanthology.org/2022.emnlp-main.357/
%U https://doi.org/10.18653/v1/2022.emnlp-main.357
%P 5326-5338
Markdown (Informal)
[DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine](https://aclanthology.org/2022.emnlp-main.357/) (Qiu et al., EMNLP 2022)
ACL
- Yifu Qiu, Hongyu Li, Yingqi Qu, Ying Chen, QiaoQiao She, Jing Liu, Hua Wu, and Haifeng Wang. 2022. DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5326–5338, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.