@inproceedings{palen-michel-etal-2025-openner,
title = "{O}pen{NER} 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languages",
author = {Palen-Michel, Chester and
Pickering, Maxwell and
Kruse, Maya and
S{\"a}lev{\"a}, Jonne and
Lignos, Constantine},
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1708/",
pages = "33637--33662",
ISBN = "979-8-89176-332-6",
abstract = "We present OpenNER 1.0, a standardized collection of openly-available named entity recognition (NER) datasets.OpenNER contains 36 NER corpora that span 52 languages, human-annotated in varying named entity ontologies.We correct annotation format issues, standardize the original datasets into a uniform representation with consistent entity type names across corpora, and provide the collection in a structure that enables research in multilingual and multi-ontology NER.We provide baseline results using three pretrained multilingual language models and two large language models to compare the performance of recent models and facilitate future research in NER.We find that no single model is best in all languages and that significant work remains to obtain high performance from LLMs on the NER task.OpenNER is released at https://github.com/bltlab/open-ner."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="palen-michel-etal-2025-openner">
<titleInfo>
<title>OpenNER 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chester</namePart>
<namePart type="family">Palen-Michel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxwell</namePart>
<namePart type="family">Pickering</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maya</namePart>
<namePart type="family">Kruse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonne</namePart>
<namePart type="family">Sälevä</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>We present OpenNER 1.0, a standardized collection of openly-available named entity recognition (NER) datasets.OpenNER contains 36 NER corpora that span 52 languages, human-annotated in varying named entity ontologies.We correct annotation format issues, standardize the original datasets into a uniform representation with consistent entity type names across corpora, and provide the collection in a structure that enables research in multilingual and multi-ontology NER.We provide baseline results using three pretrained multilingual language models and two large language models to compare the performance of recent models and facilitate future research in NER.We find that no single model is best in all languages and that significant work remains to obtain high performance from LLMs on the NER task.OpenNER is released at https://github.com/bltlab/open-ner.</abstract>
<identifier type="citekey">palen-michel-etal-2025-openner</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1708/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>33637</start>
<end>33662</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenNER 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languages
%A Palen-Michel, Chester
%A Pickering, Maxwell
%A Kruse, Maya
%A Sälevä, Jonne
%A Lignos, Constantine
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F palen-michel-etal-2025-openner
%X We present OpenNER 1.0, a standardized collection of openly-available named entity recognition (NER) datasets.OpenNER contains 36 NER corpora that span 52 languages, human-annotated in varying named entity ontologies.We correct annotation format issues, standardize the original datasets into a uniform representation with consistent entity type names across corpora, and provide the collection in a structure that enables research in multilingual and multi-ontology NER.We provide baseline results using three pretrained multilingual language models and two large language models to compare the performance of recent models and facilitate future research in NER.We find that no single model is best in all languages and that significant work remains to obtain high performance from LLMs on the NER task.OpenNER is released at https://github.com/bltlab/open-ner.
%U https://aclanthology.org/2025.emnlp-main.1708/
%P 33637-33662
Markdown (Informal)
[OpenNER 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languages](https://aclanthology.org/2025.emnlp-main.1708/) (Palen-Michel et al., EMNLP 2025)
ACL