@inproceedings{arivazhagan-etal-2023-hybrid,
title = "Hybrid Hierarchical Retrieval for Open-Domain Question Answering",
author = "Arivazhagan, Manoj Ghuhan and
Liu, Lan and
Qi, Peng and
Chen, Xinchi and
Wang, William Yang and
Huang, Zhiheng",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.679/",
doi = "10.18653/v1/2023.findings-acl.679",
pages = "10680--10689",
abstract = "Retrieval accuracy is crucial to the performance of open-domain question answering (ODQA) systems. Recent work has demonstrated that dense hierarchical retrieval (DHR), which retrieves document candidates first and then relevant passages from the refined document set, can significantly outperform the single stage dense passage retriever (DPR). While effective, this approach requires document structure information to learn document representation and is hard to adopt to other domains without this information. Additionally, the dense retrievers tend to generalize poorly on out-of-domain data comparing with sparse retrievers such as BM25. In this paper, we propose Hybrid Hierarchical Retrieval (HHR) to address the existing limitations. Instead of relying solely on dense retrievers, we can apply sparse retriever, dense retriever, and a combination of them in both stages of document and passage retrieval. We perform extensive experiments on ODQA benchmarks and observe that our framework not only brings in-domain gains, but also generalizes better to zero-shot TriviaQA and Web Questions datasets with an average of 4.69{\%} improvement on recall@100 over DHR. We also offer practical insights to trade off between retrieval accuracy, latency, and storage cost. The code is available on github."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arivazhagan-etal-2023-hybrid">
<titleInfo>
<title>Hybrid Hierarchical Retrieval for Open-Domain Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manoj</namePart>
<namePart type="given">Ghuhan</namePart>
<namePart type="family">Arivazhagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinchi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiheng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieval accuracy is crucial to the performance of open-domain question answering (ODQA) systems. Recent work has demonstrated that dense hierarchical retrieval (DHR), which retrieves document candidates first and then relevant passages from the refined document set, can significantly outperform the single stage dense passage retriever (DPR). While effective, this approach requires document structure information to learn document representation and is hard to adopt to other domains without this information. Additionally, the dense retrievers tend to generalize poorly on out-of-domain data comparing with sparse retrievers such as BM25. In this paper, we propose Hybrid Hierarchical Retrieval (HHR) to address the existing limitations. Instead of relying solely on dense retrievers, we can apply sparse retriever, dense retriever, and a combination of them in both stages of document and passage retrieval. We perform extensive experiments on ODQA benchmarks and observe that our framework not only brings in-domain gains, but also generalizes better to zero-shot TriviaQA and Web Questions datasets with an average of 4.69% improvement on recall@100 over DHR. We also offer practical insights to trade off between retrieval accuracy, latency, and storage cost. The code is available on github.</abstract>
<identifier type="citekey">arivazhagan-etal-2023-hybrid</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.679</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.679/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10680</start>
<end>10689</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hybrid Hierarchical Retrieval for Open-Domain Question Answering
%A Arivazhagan, Manoj Ghuhan
%A Liu, Lan
%A Qi, Peng
%A Chen, Xinchi
%A Wang, William Yang
%A Huang, Zhiheng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F arivazhagan-etal-2023-hybrid
%X Retrieval accuracy is crucial to the performance of open-domain question answering (ODQA) systems. Recent work has demonstrated that dense hierarchical retrieval (DHR), which retrieves document candidates first and then relevant passages from the refined document set, can significantly outperform the single stage dense passage retriever (DPR). While effective, this approach requires document structure information to learn document representation and is hard to adopt to other domains without this information. Additionally, the dense retrievers tend to generalize poorly on out-of-domain data comparing with sparse retrievers such as BM25. In this paper, we propose Hybrid Hierarchical Retrieval (HHR) to address the existing limitations. Instead of relying solely on dense retrievers, we can apply sparse retriever, dense retriever, and a combination of them in both stages of document and passage retrieval. We perform extensive experiments on ODQA benchmarks and observe that our framework not only brings in-domain gains, but also generalizes better to zero-shot TriviaQA and Web Questions datasets with an average of 4.69% improvement on recall@100 over DHR. We also offer practical insights to trade off between retrieval accuracy, latency, and storage cost. The code is available on github.
%R 10.18653/v1/2023.findings-acl.679
%U https://aclanthology.org/2023.findings-acl.679/
%U https://doi.org/10.18653/v1/2023.findings-acl.679
%P 10680-10689
Markdown (Informal)
[Hybrid Hierarchical Retrieval for Open-Domain Question Answering](https://aclanthology.org/2023.findings-acl.679/) (Arivazhagan et al., Findings 2023)
ACL