<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2021-relation-guided">
    <titleInfo>
        <title>Relation-Guided Pre-Training for Open-Domain Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ziniu</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yizhou</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kai-Wei</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Answering complex open-domain questions requires understanding the latent relations between involving entities. However, we found that the existing QA datasets are extremely imbalanced in some types of relations, which hurts the generalization performance over questions with long-tail relations. To remedy this problem, in this paper, we propose a Relation-Guided Pre-Training (RGPT-QA) framework. We first generate a relational QA dataset covering a wide range of relations from both the Wikidata triplets and Wikipedia hyperlinks. We then pre-train a QA model to infer the latent relations from the question, and then conduct extractive QA to get the target answer entity. We demonstrate that by pre-training with propoed RGPT-QA techique, the popular open-domain QA model, Dense Passage Retriever (DPR), achieves 2.2%, 2.4%, and 6.3% absolute improvement in Exact Match accuracy on Natural Questions, TriviaQA, and WebQuestions. Particularly, we show that RGPT-QA improves significantly on questions with long-tail relations.</abstract>
    <identifier type="citekey">hu-etal-2021-relation-guided</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.292</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.292/</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>3431</start>
            <end>3448</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Relation-Guided Pre-Training for Open-Domain Question Answering
%A Hu, Ziniu
%A Sun, Yizhou
%A Chang, Kai-Wei
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F hu-etal-2021-relation-guided
%X Answering complex open-domain questions requires understanding the latent relations between involving entities. However, we found that the existing QA datasets are extremely imbalanced in some types of relations, which hurts the generalization performance over questions with long-tail relations. To remedy this problem, in this paper, we propose a Relation-Guided Pre-Training (RGPT-QA) framework. We first generate a relational QA dataset covering a wide range of relations from both the Wikidata triplets and Wikipedia hyperlinks. We then pre-train a QA model to infer the latent relations from the question, and then conduct extractive QA to get the target answer entity. We demonstrate that by pre-training with propoed RGPT-QA techique, the popular open-domain QA model, Dense Passage Retriever (DPR), achieves 2.2%, 2.4%, and 6.3% absolute improvement in Exact Match accuracy on Natural Questions, TriviaQA, and WebQuestions. Particularly, we show that RGPT-QA improves significantly on questions with long-tail relations.
%R 10.18653/v1/2021.findings-emnlp.292
%U https://aclanthology.org/2021.findings-emnlp.292/
%U https://doi.org/10.18653/v1/2021.findings-emnlp.292
%P 3431-3448

Markdown (Informal)

[Relation-Guided Pre-Training for Open-Domain Question Answering](https://aclanthology.org/2021.findings-emnlp.292/) (Hu et al., Findings 2021)

• Relation-Guided Pre-Training for Open-Domain Question Answering (Hu et al., Findings 2021)

ACL

• Ziniu Hu, Yizhou Sun, and Kai-Wei Chang. 2021. Relation-Guided Pre-Training for Open-Domain Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3431–3448, Punta Cana, Dominican Republic. Association for Computational Linguistics.