@inproceedings{kim-etal-2023-relevance,
title = "Relevance-assisted Generation for Robust Zero-shot Retrieval",
author = "Kim, Jihyuk and
Kim, Minsoo and
Park, Joonsuk and
Hwang, Seung-won",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.67",
doi = "10.18653/v1/2023.emnlp-industry.67",
pages = "723--731",
abstract = "Zero-shot retrieval tasks such as the BEIR benchmark reveal out-of-domain generalization as a key weakness of high-performance dense retrievers. As a solution, domain adaptation for dense retrievers has been actively studied. A notable approach is synthesizing domain-specific data, by generating pseudo queries (PQ), for fine-tuning with domain-specific relevance between PQ and documents. Our contribution is showing that key biases can cause sampled PQ to be irrelevant, negatively contributing to generalization. We propose to preempt their generation, by dividing the generation into simpler subtasks, of generating relevance explanations and guiding the generation to avoid negative generalization. Experiment results show that our proposed approach is more robust to domain shifts, validated on challenging BEIR zero-shot retrieval tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2023-relevance">
<titleInfo>
<title>Relevance-assisted Generation for Robust Zero-shot Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jihyuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minsoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonsuk</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-shot retrieval tasks such as the BEIR benchmark reveal out-of-domain generalization as a key weakness of high-performance dense retrievers. As a solution, domain adaptation for dense retrievers has been actively studied. A notable approach is synthesizing domain-specific data, by generating pseudo queries (PQ), for fine-tuning with domain-specific relevance between PQ and documents. Our contribution is showing that key biases can cause sampled PQ to be irrelevant, negatively contributing to generalization. We propose to preempt their generation, by dividing the generation into simpler subtasks, of generating relevance explanations and guiding the generation to avoid negative generalization. Experiment results show that our proposed approach is more robust to domain shifts, validated on challenging BEIR zero-shot retrieval tasks.</abstract>
<identifier type="citekey">kim-etal-2023-relevance</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.67</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.67</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>723</start>
<end>731</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Relevance-assisted Generation for Robust Zero-shot Retrieval
%A Kim, Jihyuk
%A Kim, Minsoo
%A Park, Joonsuk
%A Hwang, Seung-won
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F kim-etal-2023-relevance
%X Zero-shot retrieval tasks such as the BEIR benchmark reveal out-of-domain generalization as a key weakness of high-performance dense retrievers. As a solution, domain adaptation for dense retrievers has been actively studied. A notable approach is synthesizing domain-specific data, by generating pseudo queries (PQ), for fine-tuning with domain-specific relevance between PQ and documents. Our contribution is showing that key biases can cause sampled PQ to be irrelevant, negatively contributing to generalization. We propose to preempt their generation, by dividing the generation into simpler subtasks, of generating relevance explanations and guiding the generation to avoid negative generalization. Experiment results show that our proposed approach is more robust to domain shifts, validated on challenging BEIR zero-shot retrieval tasks.
%R 10.18653/v1/2023.emnlp-industry.67
%U https://aclanthology.org/2023.emnlp-industry.67
%U https://doi.org/10.18653/v1/2023.emnlp-industry.67
%P 723-731
Markdown (Informal)
[Relevance-assisted Generation for Robust Zero-shot Retrieval](https://aclanthology.org/2023.emnlp-industry.67) (Kim et al., EMNLP 2023)
ACL
- Jihyuk Kim, Minsoo Kim, Joonsuk Park, and Seung-won Hwang. 2023. Relevance-assisted Generation for Robust Zero-shot Retrieval. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 723–731, Singapore. Association for Computational Linguistics.