<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albarede-etal-2023-entity">
    <titleInfo>
        <title>Entity Enhanced Attention Graph-Based Passages Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lucas</namePart>
        <namePart type="family">Albarede</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lorraine</namePart>
        <namePart type="family">Goeuriot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philippe</namePart>
        <namePart type="family">Mulhem</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Claude</namePart>
        <namePart type="family">Le Pape-Gardeux</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sylvain</namePart>
        <namePart type="family">Marie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Trinidad</namePart>
        <namePart type="family">Chardin-Segui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Actes de CORIA-TALN 2023. Actes de la 18e Conférence en Recherche d‘Information et Applications (CORIA)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Haïfa</namePart>
            <namePart type="family">Zargayouna</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ATALA</publisher>
            <place>
                <placeTerm type="text">Paris, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Passage retrieval is crucial in specialized domains where documents are long and complex, such as patents, legal documents, scientific reports, etc. We explore in this paper the integration of Entities and passages in Heterogeneous Attention Graph Models dedicated to passage retrieval. We use the two passage retrieval architectures based on re-ranking proposed in [1]. We experiment our proposal on the TREC CAR Y3 Passage Retrieval Task. The results obtained show an improvement over state-of-the-art techniques and proves the effectiveness of the approach. Our experiments also show the importance of using adequate parameters for such approach.</abstract>
    <identifier type="citekey">albarede-etal-2023-entity</identifier>
    <location>
        <url>https://aclanthology.org/2023.jeptalnrecital-coria.13/</url>
    </location>
    <part>
        <date>2023-6</date>
        <extent unit="page">
            <start>196</start>
            <end>200</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Entity Enhanced Attention Graph-Based Passages Retrieval
%A Albarede, Lucas
%A Goeuriot, Lorraine
%A Mulhem, Philippe
%A Le Pape-Gardeux, Claude
%A Marie, Sylvain
%A Chardin-Segui, Trinidad
%Y Zargayouna, Haïfa
%S Actes de CORIA-TALN 2023. Actes de la 18e Conférence en Recherche d‘Information et Applications (CORIA)
%D 2023
%8 June
%I ATALA
%C Paris, France
%F albarede-etal-2023-entity
%X Passage retrieval is crucial in specialized domains where documents are long and complex, such as patents, legal documents, scientific reports, etc. We explore in this paper the integration of Entities and passages in Heterogeneous Attention Graph Models dedicated to passage retrieval. We use the two passage retrieval architectures based on re-ranking proposed in [1]. We experiment our proposal on the TREC CAR Y3 Passage Retrieval Task. The results obtained show an improvement over state-of-the-art techniques and proves the effectiveness of the approach. Our experiments also show the importance of using adequate parameters for such approach.
%U https://aclanthology.org/2023.jeptalnrecital-coria.13/
%P 196-200

Markdown (Informal)

[Entity Enhanced Attention Graph-Based Passages Retrieval](https://aclanthology.org/2023.jeptalnrecital-coria.13/) (Albarede et al., JEP/TALN/RECITAL 2023)

• Entity Enhanced Attention Graph-Based Passages Retrieval (Albarede et al., JEP/TALN/RECITAL 2023)

ACL

• Lucas Albarede, Lorraine Goeuriot, Philippe Mulhem, Claude Le Pape-Gardeux, Sylvain Marie, and Trinidad Chardin-Segui. 2023. Entity Enhanced Attention Graph-Based Passages Retrieval. In Actes de CORIA-TALN 2023. Actes de la 18e Conférence en Recherche d'Information et Applications (CORIA), pages 196–200, Paris, France. ATALA.