<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fajcik-etal-2021-r2-d2">
    <titleInfo>
        <title>R2-D2: A Modular Baseline for Open-Domain Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Martin</namePart>
        <namePart type="family">Fajcik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martin</namePart>
        <namePart type="family">Docekal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karel</namePart>
        <namePart type="family">Ondrej</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pavel</namePart>
        <namePart type="family">Smrz</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>This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice). The pipeline is composed of a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final prediction from all system’s components. We demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA, surpassing state-of-the-art on the first two. Our analysis demonstrates that: (i) combining extractive and generative reader yields absolute improvements up to 5 exact match and it is at least twice as effective as the posterior averaging ensemble of the same models with different parameters, (ii) the extractive reader with fewer parameters can match the performance of the generative reader on extractive QA datasets.</abstract>
    <identifier type="citekey">fajcik-etal-2021-r2-d2</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.73</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.73</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>854</start>
            <end>870</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T R2-D2: A Modular Baseline for Open-Domain Question Answering
%A Fajcik, Martin
%A Docekal, Martin
%A Ondrej, Karel
%A Smrz, Pavel
%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 fajcik-etal-2021-r2-d2
%X This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice). The pipeline is composed of a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final prediction from all system’s components. We demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA, surpassing state-of-the-art on the first two. Our analysis demonstrates that: (i) combining extractive and generative reader yields absolute improvements up to 5 exact match and it is at least twice as effective as the posterior averaging ensemble of the same models with different parameters, (ii) the extractive reader with fewer parameters can match the performance of the generative reader on extractive QA datasets.
%R 10.18653/v1/2021.findings-emnlp.73
%U https://aclanthology.org/2021.findings-emnlp.73
%U https://doi.org/10.18653/v1/2021.findings-emnlp.73
%P 854-870

Markdown (Informal)

[R2-D2: A Modular Baseline for Open-Domain Question Answering](https://aclanthology.org/2021.findings-emnlp.73) (Fajcik et al., Findings 2021)

• R2-D2: A Modular Baseline for Open-Domain Question Answering (Fajcik et al., Findings 2021)

ACL

• Martin Fajcik, Martin Docekal, Karel Ondrej, and Pavel Smrz. 2021. R2-D2: A Modular Baseline for Open-Domain Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 854–870, Punta Cana, Dominican Republic. Association for Computational Linguistics.