@inproceedings{lu-etal-2024-hyrr-hybrid,
title = "{HYRR}: Hybrid Infused Reranking for Passage Retrieval",
author = "Lu, Jing and
Hall, Keith and
Ma, Ji and
Ni, Jianmo",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.748",
pages = "8528--8534",
abstract = "Existing passage retrieval systems typically adopt a two-stage retrieve-then-rerank pipeline. To obtain an effective reranking model, many prior works have focused on improving the model architectures, such as leveraging powerful pretrained large language models (LLM) and designing better objective functions. However, less attention has been paid to the issue of collecting high-quality training data. In this paper, we propose HYRR, a framework for training robust reranking models. Specifically, we propose a simple but effective approach to select training data using hybrid retrievers. Our experiments show that the rerankers trained with HYRR are robust to different first-stage retrievers. Moreover, evaluations using MS MARCO and BEIR data sets demonstrate our proposed framework effectively generalizes to both supervised and zero-shot retrieval settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2024-hyrr-hybrid">
<titleInfo>
<title>HYRR: Hybrid Infused Reranking for Passage Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Hall</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianmo</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing passage retrieval systems typically adopt a two-stage retrieve-then-rerank pipeline. To obtain an effective reranking model, many prior works have focused on improving the model architectures, such as leveraging powerful pretrained large language models (LLM) and designing better objective functions. However, less attention has been paid to the issue of collecting high-quality training data. In this paper, we propose HYRR, a framework for training robust reranking models. Specifically, we propose a simple but effective approach to select training data using hybrid retrievers. Our experiments show that the rerankers trained with HYRR are robust to different first-stage retrievers. Moreover, evaluations using MS MARCO and BEIR data sets demonstrate our proposed framework effectively generalizes to both supervised and zero-shot retrieval settings.</abstract>
<identifier type="citekey">lu-etal-2024-hyrr-hybrid</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.748</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8528</start>
<end>8534</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HYRR: Hybrid Infused Reranking for Passage Retrieval
%A Lu, Jing
%A Hall, Keith
%A Ma, Ji
%A Ni, Jianmo
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lu-etal-2024-hyrr-hybrid
%X Existing passage retrieval systems typically adopt a two-stage retrieve-then-rerank pipeline. To obtain an effective reranking model, many prior works have focused on improving the model architectures, such as leveraging powerful pretrained large language models (LLM) and designing better objective functions. However, less attention has been paid to the issue of collecting high-quality training data. In this paper, we propose HYRR, a framework for training robust reranking models. Specifically, we propose a simple but effective approach to select training data using hybrid retrievers. Our experiments show that the rerankers trained with HYRR are robust to different first-stage retrievers. Moreover, evaluations using MS MARCO and BEIR data sets demonstrate our proposed framework effectively generalizes to both supervised and zero-shot retrieval settings.
%U https://aclanthology.org/2024.lrec-main.748
%P 8528-8534
Markdown (Informal)
[HYRR: Hybrid Infused Reranking for Passage Retrieval](https://aclanthology.org/2024.lrec-main.748) (Lu et al., LREC-COLING 2024)
ACL
- Jing Lu, Keith Hall, Ji Ma, and Jianmo Ni. 2024. HYRR: Hybrid Infused Reranking for Passage Retrieval. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8528–8534, Torino, Italia. ELRA and ICCL.