@inproceedings{reichenbach-etal-2026-beyond,
title = "Beyond Dictionaries: Machine-Learned Normalization of Emission Units in Information Extraction",
author = "Reichenbach, Lisa and
Oehler, Simon and
Schierholz, Malte and
Schulten, Anna Steinberg",
editor = "Schimanski, Tobias and
Usmanova, Aida and
Morio, Gaku and
Ni, Jingwei and
Dutia, Kalyan and
Vaghefi, Seyed Saeid and
Stammbach, Dominik and
Leippold, Markus",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change ({C}limate{NLP} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.climatenlp-1.10/",
pages = "132--142",
ISBN = "979-8-89176-465-1",
abstract = "Sustainability reports denote greenhouse gas emissions with heterogeneous unit strings, such as abbreviations, inconsistent formatting, and scale markers. In emission extraction pipelines, these units must be normalized to a common target, e.g. t CO2e, to enable reliable comparison and aggregation of emissions across companies, reporting years, scopes, and regions. We propose a hybrid normalization approach: If a raw unit string is not found in a curated dictionary, a machine learning classifier maps noisy unit strings to normalized emission-unit categories that can then be converted to the target unit. The classifier is trained using character-level TF-IDF, lightweight string features, and LLM-assisted data augmentation. On random-splits of the augmented dataset, an ensemble model achieves approximately 95{\%} accuracy. Additional evaluation on rare real-world unit strings indicates that supervised fallback classifiers can handle out-of-dictionary variants in climate-related information extraction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reichenbach-etal-2026-beyond">
<titleInfo>
<title>Beyond Dictionaries: Machine-Learned Normalization of Emission Units in Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Reichenbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Oehler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malte</namePart>
<namePart type="family">Schierholz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="given">Steinberg</namePart>
<namePart type="family">Schulten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)</title>
</titleInfo>
<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">Aida</namePart>
<namePart type="family">Usmanova</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">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Seyed</namePart>
<namePart type="given">Saeid</namePart>
<namePart type="family">Vaghefi</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">Markus</namePart>
<namePart type="family">Leippold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-465-1</identifier>
</relatedItem>
<abstract>Sustainability reports denote greenhouse gas emissions with heterogeneous unit strings, such as abbreviations, inconsistent formatting, and scale markers. In emission extraction pipelines, these units must be normalized to a common target, e.g. t CO2e, to enable reliable comparison and aggregation of emissions across companies, reporting years, scopes, and regions. We propose a hybrid normalization approach: If a raw unit string is not found in a curated dictionary, a machine learning classifier maps noisy unit strings to normalized emission-unit categories that can then be converted to the target unit. The classifier is trained using character-level TF-IDF, lightweight string features, and LLM-assisted data augmentation. On random-splits of the augmented dataset, an ensemble model achieves approximately 95% accuracy. Additional evaluation on rare real-world unit strings indicates that supervised fallback classifiers can handle out-of-dictionary variants in climate-related information extraction.</abstract>
<identifier type="citekey">reichenbach-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.10/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>132</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Dictionaries: Machine-Learned Normalization of Emission Units in Information Extraction
%A Reichenbach, Lisa
%A Oehler, Simon
%A Schierholz, Malte
%A Schulten, Anna Steinberg
%Y Schimanski, Tobias
%Y Usmanova, Aida
%Y Morio, Gaku
%Y Ni, Jingwei
%Y Dutia, Kalyan
%Y Vaghefi, Seyed Saeid
%Y Stammbach, Dominik
%Y Leippold, Markus
%S Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-465-1
%F reichenbach-etal-2026-beyond
%X Sustainability reports denote greenhouse gas emissions with heterogeneous unit strings, such as abbreviations, inconsistent formatting, and scale markers. In emission extraction pipelines, these units must be normalized to a common target, e.g. t CO2e, to enable reliable comparison and aggregation of emissions across companies, reporting years, scopes, and regions. We propose a hybrid normalization approach: If a raw unit string is not found in a curated dictionary, a machine learning classifier maps noisy unit strings to normalized emission-unit categories that can then be converted to the target unit. The classifier is trained using character-level TF-IDF, lightweight string features, and LLM-assisted data augmentation. On random-splits of the augmented dataset, an ensemble model achieves approximately 95% accuracy. Additional evaluation on rare real-world unit strings indicates that supervised fallback classifiers can handle out-of-dictionary variants in climate-related information extraction.
%U https://aclanthology.org/2026.climatenlp-1.10/
%P 132-142
Markdown (Informal)
[Beyond Dictionaries: Machine-Learned Normalization of Emission Units in Information Extraction](https://aclanthology.org/2026.climatenlp-1.10/) (Reichenbach et al., ClimateNLP 2026)
ACL