<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stammbach-2021-evidence">
    <titleInfo>
        <title>Evidence Selection as a Token-Level Prediction Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dominik</namePart>
        <namePart type="family">Stammbach</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>Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Rami</namePart>
            <namePart type="family">Aly</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Oana</namePart>
            <namePart type="family">Cocarascu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zhijiang</namePart>
            <namePart type="family">Guo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arpit</namePart>
            <namePart type="family">Mittal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">Schlichtkrull</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">James</namePart>
            <namePart type="family">Thorne</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In Automated Claim Verification, we retrieve evidence from a knowledge base to determine the veracity of a claim. Intuitively, the retrieval of the correct evidence plays a crucial role in this process. Often, evidence selection is tackled as a pairwise sentence classification task, i.e., we train a model to predict for each sentence individually whether it is evidence for a claim. In this work, we fine-tune document level transformers to extract all evidence from a Wikipedia document at once. We show that this approach performs better than a comparable model classifying sentences individually on all relevant evidence selection metrics in FEVER. Our complete pipeline building on this evidence selection procedure produces a new state-of-the-art result on FEVER, a popular claim verification benchmark.</abstract>
    <identifier type="citekey">stammbach-2021-evidence</identifier>
    <identifier type="doi">10.18653/v1/2021.fever-1.2</identifier>
    <location>
        <url>https://aclanthology.org/2021.fever-1.2</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>14</start>
            <end>20</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evidence Selection as a Token-Level Prediction Task
%A Stammbach, Dominik
%Y Aly, Rami
%Y Christodoulopoulos, Christos
%Y Cocarascu, Oana
%Y Guo, Zhijiang
%Y Mittal, Arpit
%Y Schlichtkrull, Michael
%Y Thorne, James
%Y Vlachos, Andreas
%S Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Dominican Republic
%F stammbach-2021-evidence
%X In Automated Claim Verification, we retrieve evidence from a knowledge base to determine the veracity of a claim. Intuitively, the retrieval of the correct evidence plays a crucial role in this process. Often, evidence selection is tackled as a pairwise sentence classification task, i.e., we train a model to predict for each sentence individually whether it is evidence for a claim. In this work, we fine-tune document level transformers to extract all evidence from a Wikipedia document at once. We show that this approach performs better than a comparable model classifying sentences individually on all relevant evidence selection metrics in FEVER. Our complete pipeline building on this evidence selection procedure produces a new state-of-the-art result on FEVER, a popular claim verification benchmark.
%R 10.18653/v1/2021.fever-1.2
%U https://aclanthology.org/2021.fever-1.2
%U https://doi.org/10.18653/v1/2021.fever-1.2
%P 14-20

Markdown (Informal)

[Evidence Selection as a Token-Level Prediction Task](https://aclanthology.org/2021.fever-1.2) (Stammbach, FEVER 2021)

• Evidence Selection as a Token-Level Prediction Task (Stammbach, FEVER 2021)

ACL

• Dominik Stammbach. 2021. Evidence Selection as a Token-Level Prediction Task. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), pages 14–20, Dominican Republic. Association for Computational Linguistics.