<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2023-dreeam">
    <titleInfo>
        <title>DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Youmi</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">An</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Naoaki</namePart>
        <namePart type="family">Okazaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Document-level relation extraction (DocRE) is the task of identifying all relations between each entity pair in a document. Evidence, defined as sentences containing clues for the relationship between an entity pair, has been shown to help DocRE systems focus on relevant texts, thus improving relation extraction. However, evidence retrieval (ER) in DocRE faces two major issues: high memory consumption and limited availability of annotations. This work aims at addressing these issues to improve the usage of ER in DocRE. First, we propose DREEAM, a memory-efficient approach that adopts evidence information as the supervisory signal, thereby guiding the attention modules of the DocRE system to assign high weights to evidence. Second, we propose a self-training strategy for DREEAM to learn ER from automatically-generated evidence on massive data without evidence annotations. Experimental results reveal that our approach exhibits state-of-the-art performance on the DocRED benchmark for both DocRE and ER. To the best of our knowledge, DREEAM is the first approach to employ ER self-training.</abstract>
    <identifier type="citekey">ma-etal-2023-dreeam</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.145</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.145</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1971</start>
            <end>1983</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction
%A Ma, Youmi
%A Wang, An
%A Okazaki, Naoaki
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F ma-etal-2023-dreeam
%X Document-level relation extraction (DocRE) is the task of identifying all relations between each entity pair in a document. Evidence, defined as sentences containing clues for the relationship between an entity pair, has been shown to help DocRE systems focus on relevant texts, thus improving relation extraction. However, evidence retrieval (ER) in DocRE faces two major issues: high memory consumption and limited availability of annotations. This work aims at addressing these issues to improve the usage of ER in DocRE. First, we propose DREEAM, a memory-efficient approach that adopts evidence information as the supervisory signal, thereby guiding the attention modules of the DocRE system to assign high weights to evidence. Second, we propose a self-training strategy for DREEAM to learn ER from automatically-generated evidence on massive data without evidence annotations. Experimental results reveal that our approach exhibits state-of-the-art performance on the DocRED benchmark for both DocRE and ER. To the best of our knowledge, DREEAM is the first approach to employ ER self-training.
%R 10.18653/v1/2023.eacl-main.145
%U https://aclanthology.org/2023.eacl-main.145
%U https://doi.org/10.18653/v1/2023.eacl-main.145
%P 1971-1983

Markdown (Informal)

[DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction](https://aclanthology.org/2023.eacl-main.145) (Ma et al., EACL 2023)

• DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction (Ma et al., EACL 2023)

ACL

• Youmi Ma, An Wang, and Naoaki Okazaki. 2023. DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1971–1983, Dubrovnik, Croatia. Association for Computational Linguistics.