@inproceedings{pan-etal-2025-climateie,
title = "{C}limate{IE}: A Dataset for Climate Science Information Extraction",
author = "Pan, Huitong and
Adamu, Mustapha and
Zhang, Qi and
Dragut, Eduard and
Latecki, Longin Jan",
editor = "Dutia, Kalyan and
Henderson, Peter and
Leippold, Markus and
Manning, Christoper and
Morio, Gaku and
Muccione, Veruska and
Ni, Jingwei and
Schimanski, Tobias and
Stammbach, Dominik and
Singh, Alok and
Su, Alba (Ruiran) and
A. Vaghefi, Saeid",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.climatenlp-1.6/",
doi = "10.18653/v1/2025.climatenlp-1.6",
pages = "76--98",
ISBN = "979-8-89176-259-6",
abstract = "The rapid growth of climate science literature necessitates advanced information extraction (IE) systems to structure knowledge for researchers and policymakers. We introduce ClimateIE, a novel framework combining taxonomy-guided large language model (LLM) annotation with expert validation to address three core tasks: climate-specific named entity recognition, relationship extraction, and entity linking. Our contributions include: (1) the ClimateIE-Corpus{---}500 climate publications annotated via a hybrid human-AI pipeline with mappings to the extended GCMD+ taxonomy; (2) systematic evaluation showing Llama-3.3-70B achieves state-of-the-art performance (strict F1: 0.378 NER, 0.367 EL), outperforming larger commercial models (GPT-4o) and domain-adapted baselines (ClimateGPT) by 11-58{\%}; and (3) analysis revealing critical challenges in technical relationship extraction (MountedOn: 0.000 F1) and emerging concept linking (26.4{\%} unlinkable entities). Upon acceptance, we will release the corpus, toolkit, and guidelines to advance climate informatics, establishing benchmarks for NLP in Earth system science and underscoring the need for dynamic taxonomy governance and implicit relationship modeling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-etal-2025-climateie">
<titleInfo>
<title>ClimateIE: A Dataset for Climate Science Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huitong</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustapha</namePart>
<namePart type="family">Adamu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Dragut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longin</namePart>
<namePart type="given">Jan</namePart>
<namePart type="family">Latecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Henderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoper</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veruska</namePart>
<namePart type="family">Muccione</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alba</namePart>
<namePart type="given">(Ruiran)</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saeid</namePart>
<namePart type="family">A. Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-259-6</identifier>
</relatedItem>
<abstract>The rapid growth of climate science literature necessitates advanced information extraction (IE) systems to structure knowledge for researchers and policymakers. We introduce ClimateIE, a novel framework combining taxonomy-guided large language model (LLM) annotation with expert validation to address three core tasks: climate-specific named entity recognition, relationship extraction, and entity linking. Our contributions include: (1) the ClimateIE-Corpus—500 climate publications annotated via a hybrid human-AI pipeline with mappings to the extended GCMD+ taxonomy; (2) systematic evaluation showing Llama-3.3-70B achieves state-of-the-art performance (strict F1: 0.378 NER, 0.367 EL), outperforming larger commercial models (GPT-4o) and domain-adapted baselines (ClimateGPT) by 11-58%; and (3) analysis revealing critical challenges in technical relationship extraction (MountedOn: 0.000 F1) and emerging concept linking (26.4% unlinkable entities). Upon acceptance, we will release the corpus, toolkit, and guidelines to advance climate informatics, establishing benchmarks for NLP in Earth system science and underscoring the need for dynamic taxonomy governance and implicit relationship modeling.</abstract>
<identifier type="citekey">pan-etal-2025-climateie</identifier>
<identifier type="doi">10.18653/v1/2025.climatenlp-1.6</identifier>
<location>
<url>https://aclanthology.org/2025.climatenlp-1.6/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>76</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ClimateIE: A Dataset for Climate Science Information Extraction
%A Pan, Huitong
%A Adamu, Mustapha
%A Zhang, Qi
%A Dragut, Eduard
%A Latecki, Longin Jan
%Y Dutia, Kalyan
%Y Henderson, Peter
%Y Leippold, Markus
%Y Manning, Christoper
%Y Morio, Gaku
%Y Muccione, Veruska
%Y Ni, Jingwei
%Y Schimanski, Tobias
%Y Stammbach, Dominik
%Y Singh, Alok
%Y Su, Alba (Ruiran)
%Y A. Vaghefi, Saeid
%S Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-259-6
%F pan-etal-2025-climateie
%X The rapid growth of climate science literature necessitates advanced information extraction (IE) systems to structure knowledge for researchers and policymakers. We introduce ClimateIE, a novel framework combining taxonomy-guided large language model (LLM) annotation with expert validation to address three core tasks: climate-specific named entity recognition, relationship extraction, and entity linking. Our contributions include: (1) the ClimateIE-Corpus—500 climate publications annotated via a hybrid human-AI pipeline with mappings to the extended GCMD+ taxonomy; (2) systematic evaluation showing Llama-3.3-70B achieves state-of-the-art performance (strict F1: 0.378 NER, 0.367 EL), outperforming larger commercial models (GPT-4o) and domain-adapted baselines (ClimateGPT) by 11-58%; and (3) analysis revealing critical challenges in technical relationship extraction (MountedOn: 0.000 F1) and emerging concept linking (26.4% unlinkable entities). Upon acceptance, we will release the corpus, toolkit, and guidelines to advance climate informatics, establishing benchmarks for NLP in Earth system science and underscoring the need for dynamic taxonomy governance and implicit relationship modeling.
%R 10.18653/v1/2025.climatenlp-1.6
%U https://aclanthology.org/2025.climatenlp-1.6/
%U https://doi.org/10.18653/v1/2025.climatenlp-1.6
%P 76-98
Markdown (Informal)
[ClimateIE: A Dataset for Climate Science Information Extraction](https://aclanthology.org/2025.climatenlp-1.6/) (Pan et al., ClimateNLP 2025)
ACL
- Huitong Pan, Mustapha Adamu, Qi Zhang, Eduard Dragut, and Longin Jan Latecki. 2025. ClimateIE: A Dataset for Climate Science Information Extraction. In Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025), pages 76–98, Vienna, Austria. Association for Computational Linguistics.