@inproceedings{dsouza-etal-2026-extreme,
title = "An Extreme Multi-label Text Classification ({XMTC}) Library Dataset: What If We Took ``Use of Practical {AI} in Digital Libraries'' Seriously?",
author = "D{'}Souza, Jennifer and
Sadruddin, Sameer and
Kaehler, Maximilian and
Salfinger, Andrea and
Zaccagna, Luca and
Incitti, Francesca and
Snidaro, Lauro and
Suominen, Osma",
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-1.12/",
doi = "10.63317/5kag6gjg636f",
pages = "169--184",
abstract = "Subject indexing is vital for discovery but hard to sustain at scale and across languages. We release a large bilingual (English/German) corpus of catalog records annotated with the Integrated Authority File (GND), plus a machine-actionable GND taxonomy. The resource enables ontology-aware multi-label classification, mapping text to authority terms, and agent-assisted cataloging with reproducible, authority-grounded evaluation. We provide a brief statistical profile and qualitative error analyses of three systems. We invite the community to assess not only accuracy but usefulness and transparency, toward authority-anchored AI co-pilots that amplify catalogers' work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dsouza-etal-2026-extreme">
<titleInfo>
<title>An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took “Use of Practical AI in Digital Libraries” Seriously?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">D’Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Sadruddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Kaehler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Salfinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Zaccagna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Incitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lauro</namePart>
<namePart type="family">Snidaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osma</namePart>
<namePart type="family">Suominen</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>Subject indexing is vital for discovery but hard to sustain at scale and across languages. We release a large bilingual (English/German) corpus of catalog records annotated with the Integrated Authority File (GND), plus a machine-actionable GND taxonomy. The resource enables ontology-aware multi-label classification, mapping text to authority terms, and agent-assisted cataloging with reproducible, authority-grounded evaluation. We provide a brief statistical profile and qualitative error analyses of three systems. We invite the community to assess not only accuracy but usefulness and transparency, toward authority-anchored AI co-pilots that amplify catalogers’ work.</abstract>
<identifier type="citekey">dsouza-etal-2026-extreme</identifier>
<identifier type="doi">10.63317/5kag6gjg636f</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.12/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>169</start>
<end>184</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took “Use of Practical AI in Digital Libraries” Seriously?
%A D’Souza, Jennifer
%A Sadruddin, Sameer
%A Kaehler, Maximilian
%A Salfinger, Andrea
%A Zaccagna, Luca
%A Incitti, Francesca
%A Snidaro, Lauro
%A Suominen, Osma
%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 dsouza-etal-2026-extreme
%X Subject indexing is vital for discovery but hard to sustain at scale and across languages. We release a large bilingual (English/German) corpus of catalog records annotated with the Integrated Authority File (GND), plus a machine-actionable GND taxonomy. The resource enables ontology-aware multi-label classification, mapping text to authority terms, and agent-assisted cataloging with reproducible, authority-grounded evaluation. We provide a brief statistical profile and qualitative error analyses of three systems. We invite the community to assess not only accuracy but usefulness and transparency, toward authority-anchored AI co-pilots that amplify catalogers’ work.
%R 10.63317/5kag6gjg636f
%U https://aclanthology.org/2026.lrec-1.12/
%U https://doi.org/10.63317/5kag6gjg636f
%P 169-184
Markdown (Informal)
[An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took "Use of Practical AI in Digital Libraries" Seriously?](https://aclanthology.org/2026.lrec-1.12/) (D’Souza et al., LREC 2026)
ACL
- Jennifer D’Souza, Sameer Sadruddin, Maximilian Kaehler, Andrea Salfinger, Luca Zaccagna, Francesca Incitti, Lauro Snidaro, and Osma Suominen. 2026. An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took "Use of Practical AI in Digital Libraries" Seriously?. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 169–184, Palma de Mallorca, Spain. ELRA Language Resource Association.