@inproceedings{nedellec-etal-2026-epop,
title = "{EPOP}: A Benchmark Corpus for Assessing {NLP} Models on Structured Information Extraction in Plant Health",
author = "Nedellec, Claire and
Courtin, Marine and
Yao, Xinzhi and
Grosdidier, Marie and
Pieretti, Isabelle and
Duperier, Sandy and
Bossy, Robert",
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-1.103/",
doi = "10.63317/4in2fpefq4pz",
pages = "1331--1340",
abstract = "We introduce the EPOP (Epidemiomonitoring of Plants) corpus, a new annotated resource for structured information extraction in the domain of plant health epidemiology. The corpus consists of translated news reports that reflect real-world phytosanitary monitoring scenarios. It includes annotations for named entities (e.g. Plant, Pest, Vector, Disease, Dissemination Pathway), identity coreferences, and both binary and complex n-ary relations that represent key events such as Transmits or Causes, along with their modalities. A distinctive feature of EPOP is its normalization layer where mentions of species and geographical locations are linked to canonical identifiers in the NCBI Taxonomy and GeoNames, enabling semantic disambiguation and integration with external knowledge bases. As the first publicly available corpus of its kind, EPOP presents a realistic and challenging benchmark, with high linguistic variability, entity role ambiguity, and long-distance relations. We report baseline results on core tasks (named entity recognition, normalization (entity-linking), and relation extraction) using both fine-tuned BERT-based models and hard-prompted large language models. These experiments demonstrate the utility of EPOP while also identifying areas for improvement, particularly in the extraction of complex relations. The corpus is released under an open license, to support research in environmental NLP, crop protection, and knowledge graph enrichment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nedellec-etal-2026-epop">
<titleInfo>
<title>EPOP: A Benchmark Corpus for Assessing NLP Models on Structured Information Extraction in Plant Health</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Nedellec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Courtin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinzhi</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Grosdidier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Pieretti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandy</namePart>
<namePart type="family">Duperier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Bossy</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>We introduce the EPOP (Epidemiomonitoring of Plants) corpus, a new annotated resource for structured information extraction in the domain of plant health epidemiology. The corpus consists of translated news reports that reflect real-world phytosanitary monitoring scenarios. It includes annotations for named entities (e.g. Plant, Pest, Vector, Disease, Dissemination Pathway), identity coreferences, and both binary and complex n-ary relations that represent key events such as Transmits or Causes, along with their modalities. A distinctive feature of EPOP is its normalization layer where mentions of species and geographical locations are linked to canonical identifiers in the NCBI Taxonomy and GeoNames, enabling semantic disambiguation and integration with external knowledge bases. As the first publicly available corpus of its kind, EPOP presents a realistic and challenging benchmark, with high linguistic variability, entity role ambiguity, and long-distance relations. We report baseline results on core tasks (named entity recognition, normalization (entity-linking), and relation extraction) using both fine-tuned BERT-based models and hard-prompted large language models. These experiments demonstrate the utility of EPOP while also identifying areas for improvement, particularly in the extraction of complex relations. The corpus is released under an open license, to support research in environmental NLP, crop protection, and knowledge graph enrichment.</abstract>
<identifier type="citekey">nedellec-etal-2026-epop</identifier>
<identifier type="doi">10.63317/4in2fpefq4pz</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.103/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1331</start>
<end>1340</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EPOP: A Benchmark Corpus for Assessing NLP Models on Structured Information Extraction in Plant Health
%A Nedellec, Claire
%A Courtin, Marine
%A Yao, Xinzhi
%A Grosdidier, Marie
%A Pieretti, Isabelle
%A Duperier, Sandy
%A Bossy, Robert
%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 nedellec-etal-2026-epop
%X We introduce the EPOP (Epidemiomonitoring of Plants) corpus, a new annotated resource for structured information extraction in the domain of plant health epidemiology. The corpus consists of translated news reports that reflect real-world phytosanitary monitoring scenarios. It includes annotations for named entities (e.g. Plant, Pest, Vector, Disease, Dissemination Pathway), identity coreferences, and both binary and complex n-ary relations that represent key events such as Transmits or Causes, along with their modalities. A distinctive feature of EPOP is its normalization layer where mentions of species and geographical locations are linked to canonical identifiers in the NCBI Taxonomy and GeoNames, enabling semantic disambiguation and integration with external knowledge bases. As the first publicly available corpus of its kind, EPOP presents a realistic and challenging benchmark, with high linguistic variability, entity role ambiguity, and long-distance relations. We report baseline results on core tasks (named entity recognition, normalization (entity-linking), and relation extraction) using both fine-tuned BERT-based models and hard-prompted large language models. These experiments demonstrate the utility of EPOP while also identifying areas for improvement, particularly in the extraction of complex relations. The corpus is released under an open license, to support research in environmental NLP, crop protection, and knowledge graph enrichment.
%R 10.63317/4in2fpefq4pz
%U https://aclanthology.org/2026.lrec-1.103/
%U https://doi.org/10.63317/4in2fpefq4pz
%P 1331-1340
Markdown (Informal)
[EPOP: A Benchmark Corpus for Assessing NLP Models on Structured Information Extraction in Plant Health](https://aclanthology.org/2026.lrec-1.103/) (Nedellec et al., LREC 2026)
ACL