@inproceedings{cai-etal-2026-relation,
title = "Relation Extraction across Entire Books to Reconstruct Community Networks: The {A}ffil{KG} Datasets",
author = "Cai, Erica and
Mcquade, Sean and
Young, Kevin and
O{'}Connor, Brendan",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.615/",
doi = "10.63317/4ddnnhq4dpfn",
pages = "7744--7754",
abstract = "When knowledge graphs (KGs) are automatically extracted from text, are they accurate enough for downstream analysis? Unfortunately, current annotated datasets cannot be used to evaluate this question, since the knowledge graphs they correspond to, constructed by mapping entities in the text to nodes and relations to edges, are typically highly disconnected, too small, or overly complex. To address this gap, we introduce \textsc{AffilKG}, which is a collection of six datasets that are the first to pair complete book scans with large, labeled knowledge graphs. Each dataset features affiliation graphs, which are simple KGs that capture \textsc{Member} relationships between \textsc{Person} and \textsc{Organization} entities{---}useful in studies of migration, community interactions, and other social phenomena. In addition, three datasets include expanded KGs with a wider variety of relation types. Our preliminary experiments demonstrate significant variability in model performance across datasets, underscoring \textsc{AffilKG}{'}s ability to enable two critical advances: (1) benchmarking how extraction errors propagate to graph-level analyses (e.g., community structure), and (2) validating KG extraction methods for real-world social science research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cai-etal-2026-relation">
<titleInfo>
<title>Relation Extraction across Entire Books to Reconstruct Community Networks: The AffilKG Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erica</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">Mcquade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brendan</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When knowledge graphs (KGs) are automatically extracted from text, are they accurate enough for downstream analysis? Unfortunately, current annotated datasets cannot be used to evaluate this question, since the knowledge graphs they correspond to, constructed by mapping entities in the text to nodes and relations to edges, are typically highly disconnected, too small, or overly complex. To address this gap, we introduce AffilKG, which is a collection of six datasets that are the first to pair complete book scans with large, labeled knowledge graphs. Each dataset features affiliation graphs, which are simple KGs that capture Member relationships between Person and Organization entities—useful in studies of migration, community interactions, and other social phenomena. In addition, three datasets include expanded KGs with a wider variety of relation types. Our preliminary experiments demonstrate significant variability in model performance across datasets, underscoring AffilKG’s ability to enable two critical advances: (1) benchmarking how extraction errors propagate to graph-level analyses (e.g., community structure), and (2) validating KG extraction methods for real-world social science research.</abstract>
<identifier type="citekey">cai-etal-2026-relation</identifier>
<identifier type="doi">10.63317/4ddnnhq4dpfn</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.615/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7744</start>
<end>7754</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Relation Extraction across Entire Books to Reconstruct Community Networks: The AffilKG Datasets
%A Cai, Erica
%A Mcquade, Sean
%A Young, Kevin
%A O’Connor, Brendan
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F cai-etal-2026-relation
%X When knowledge graphs (KGs) are automatically extracted from text, are they accurate enough for downstream analysis? Unfortunately, current annotated datasets cannot be used to evaluate this question, since the knowledge graphs they correspond to, constructed by mapping entities in the text to nodes and relations to edges, are typically highly disconnected, too small, or overly complex. To address this gap, we introduce AffilKG, which is a collection of six datasets that are the first to pair complete book scans with large, labeled knowledge graphs. Each dataset features affiliation graphs, which are simple KGs that capture Member relationships between Person and Organization entities—useful in studies of migration, community interactions, and other social phenomena. In addition, three datasets include expanded KGs with a wider variety of relation types. Our preliminary experiments demonstrate significant variability in model performance across datasets, underscoring AffilKG’s ability to enable two critical advances: (1) benchmarking how extraction errors propagate to graph-level analyses (e.g., community structure), and (2) validating KG extraction methods for real-world social science research.
%R 10.63317/4ddnnhq4dpfn
%U https://aclanthology.org/2026.lrec-1.615/
%U https://doi.org/10.63317/4ddnnhq4dpfn
%P 7744-7754
Markdown (Informal)
[Relation Extraction across Entire Books to Reconstruct Community Networks: The AffilKG Datasets](https://aclanthology.org/2026.lrec-1.615/) (Cai et al., LREC 2026)
ACL