@inproceedings{ishisaka-2026-ontology,
title = "Ontology-Guided Query Expansion for Evidence Retrieval in {ESRS} {E}1 Climate Disclosures",
author = "Ishisaka, Tatsuya",
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-1.8/",
pages = "116--123",
ISBN = "979-8-89176-465-1",
abstract = "Auditable analysis of corporate climate disclosures requires retrieving, for each regulatory disclosure requirement, the report page or section that contains the evidence. We study ontology-aware query expansion (OAE) for ESRS E1 (Climate Change) requirements over a new page/section-level benchmark: five companies, 1,177 real-artifact chunks, and 114 human-reviewed gold labels, plus a held-out ESRS-native company (64 labels) unseen during ontology construction. Against lexical, dense, hybrid, and pseudo-relevance-feedback (PRF) baselines, a lightweight ontology built from the standard{'}s requirements improves retrieval: the best configuration reaches Recall@10 0.842 vs. BM25{'}s 0.702 (McNemar $p=.003$). Generic PRF expansion hurts retrieval while ontology-guided expansion helps; a corpus-blind LLM query expander is a far stronger control and ties with the ontology in-domain, but does not transfer to the held-out company, where OAE stays ahead of lexical, dense, and LLM-expansion baselines while being statistically indistinguishable from cross-encoder reranking {---} a comparison we treat as diagnostic rather than conclusive. We provide an error analysis of the residual misses. ``Gold'' denotes retrieval ground truth only; we make no company scoring or compliance judgement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ishisaka-2026-ontology">
<titleInfo>
<title>Ontology-Guided Query Expansion for Evidence Retrieval in ESRS E1 Climate Disclosures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Ishisaka</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>Auditable analysis of corporate climate disclosures requires retrieving, for each regulatory disclosure requirement, the report page or section that contains the evidence. We study ontology-aware query expansion (OAE) for ESRS E1 (Climate Change) requirements over a new page/section-level benchmark: five companies, 1,177 real-artifact chunks, and 114 human-reviewed gold labels, plus a held-out ESRS-native company (64 labels) unseen during ontology construction. Against lexical, dense, hybrid, and pseudo-relevance-feedback (PRF) baselines, a lightweight ontology built from the standard’s requirements improves retrieval: the best configuration reaches Recall@10 0.842 vs. BM25’s 0.702 (McNemar p=.003). Generic PRF expansion hurts retrieval while ontology-guided expansion helps; a corpus-blind LLM query expander is a far stronger control and ties with the ontology in-domain, but does not transfer to the held-out company, where OAE stays ahead of lexical, dense, and LLM-expansion baselines while being statistically indistinguishable from cross-encoder reranking — a comparison we treat as diagnostic rather than conclusive. We provide an error analysis of the residual misses. “Gold” denotes retrieval ground truth only; we make no company scoring or compliance judgement.</abstract>
<identifier type="citekey">ishisaka-2026-ontology</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>116</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ontology-Guided Query Expansion for Evidence Retrieval in ESRS E1 Climate Disclosures
%A Ishisaka, Tatsuya
%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 ishisaka-2026-ontology
%X Auditable analysis of corporate climate disclosures requires retrieving, for each regulatory disclosure requirement, the report page or section that contains the evidence. We study ontology-aware query expansion (OAE) for ESRS E1 (Climate Change) requirements over a new page/section-level benchmark: five companies, 1,177 real-artifact chunks, and 114 human-reviewed gold labels, plus a held-out ESRS-native company (64 labels) unseen during ontology construction. Against lexical, dense, hybrid, and pseudo-relevance-feedback (PRF) baselines, a lightweight ontology built from the standard’s requirements improves retrieval: the best configuration reaches Recall@10 0.842 vs. BM25’s 0.702 (McNemar p=.003). Generic PRF expansion hurts retrieval while ontology-guided expansion helps; a corpus-blind LLM query expander is a far stronger control and ties with the ontology in-domain, but does not transfer to the held-out company, where OAE stays ahead of lexical, dense, and LLM-expansion baselines while being statistically indistinguishable from cross-encoder reranking — a comparison we treat as diagnostic rather than conclusive. We provide an error analysis of the residual misses. “Gold” denotes retrieval ground truth only; we make no company scoring or compliance judgement.
%U https://aclanthology.org/2026.climatenlp-1.8/
%P 116-123
Markdown (Informal)
[Ontology-Guided Query Expansion for Evidence Retrieval in ESRS E1 Climate Disclosures](https://aclanthology.org/2026.climatenlp-1.8/) (Ishisaka, ClimateNLP 2026)
ACL