@inproceedings{huang-etal-2022-mixed,
title = "Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in {O}pen{QA}",
author = "Huang, Junjie and
Zhong, Wanjun and
Liu, Qian and
Gong, Ming and
Jiang, Daxin and
Duan, Nan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.303",
doi = "10.18653/v1/2022.findings-emnlp.303",
pages = "4117--4129",
abstract = "Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to the challenges of table-text discrepancy and data sparsity problem. To address the above challenges, we introduce an optimized OpenQA Table-Text Retriever (OTTeR) to jointly retrieve tabular and textual evidences. Firstly, we propose to enhance mixed-modality representation learning via two mechanisms: modality-enhanced representation and mixed-modality negative sampling strategy. Secondly, to alleviate data sparsity problem and enhance the general retrieval ability, we conduct retrieval-centric mixed-modality synthetic pre-training. Experimental results demonstrate that OTTeR substantially improves the performance of table-and-text retrieval on the OTT-QA dataset. Comprehensive analyses examine the effectiveness of all the proposed mechanisms. Besides, equipped with OTTeR, our OpenQA system achieves the state-of-the-art result on the downstream QA task, with 10.1{\%} absolute improvement in terms of the exact match over the previous best system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-mixed">
<titleInfo>
<title>Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanjun</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daxin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Duan</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>Findings of the Association for Computational Linguistics: EMNLP 2022</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>Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to the challenges of table-text discrepancy and data sparsity problem. To address the above challenges, we introduce an optimized OpenQA Table-Text Retriever (OTTeR) to jointly retrieve tabular and textual evidences. Firstly, we propose to enhance mixed-modality representation learning via two mechanisms: modality-enhanced representation and mixed-modality negative sampling strategy. Secondly, to alleviate data sparsity problem and enhance the general retrieval ability, we conduct retrieval-centric mixed-modality synthetic pre-training. Experimental results demonstrate that OTTeR substantially improves the performance of table-and-text retrieval on the OTT-QA dataset. Comprehensive analyses examine the effectiveness of all the proposed mechanisms. Besides, equipped with OTTeR, our OpenQA system achieves the state-of-the-art result on the downstream QA task, with 10.1% absolute improvement in terms of the exact match over the previous best system.</abstract>
<identifier type="citekey">huang-etal-2022-mixed</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.303</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.303</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4117</start>
<end>4129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA
%A Huang, Junjie
%A Zhong, Wanjun
%A Liu, Qian
%A Gong, Ming
%A Jiang, Daxin
%A Duan, Nan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F huang-etal-2022-mixed
%X Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to the challenges of table-text discrepancy and data sparsity problem. To address the above challenges, we introduce an optimized OpenQA Table-Text Retriever (OTTeR) to jointly retrieve tabular and textual evidences. Firstly, we propose to enhance mixed-modality representation learning via two mechanisms: modality-enhanced representation and mixed-modality negative sampling strategy. Secondly, to alleviate data sparsity problem and enhance the general retrieval ability, we conduct retrieval-centric mixed-modality synthetic pre-training. Experimental results demonstrate that OTTeR substantially improves the performance of table-and-text retrieval on the OTT-QA dataset. Comprehensive analyses examine the effectiveness of all the proposed mechanisms. Besides, equipped with OTTeR, our OpenQA system achieves the state-of-the-art result on the downstream QA task, with 10.1% absolute improvement in terms of the exact match over the previous best system.
%R 10.18653/v1/2022.findings-emnlp.303
%U https://aclanthology.org/2022.findings-emnlp.303
%U https://doi.org/10.18653/v1/2022.findings-emnlp.303
%P 4117-4129
Markdown (Informal)
[Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA](https://aclanthology.org/2022.findings-emnlp.303) (Huang et al., Findings 2022)
ACL