@inproceedings{kunananthaseelan-etal-2026-ontoform,
title = "{ONTOFORM}: Ontology-Grounded Semantic Data Generation for Enterprise Document Understanding",
author = "Kunananthaseelan, Nilakshan and
Kane, Benjamin and
Jain, Siddharth and
Ghorbanali, Mahsa and
Shiri, Fatemeh and
Tumuluri, Raj and
Haffari, Gholamreza",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.210/",
pages = "3535--3543",
ISBN = "979-8-89176-460-6",
abstract = "Enterprise forms are layout-specific observations of real-world entities whose semantics span fields, recurring sections and related documents. Developing enterprise document-understanding systems requires large-scale supervision, but obtaining authentic forms is constrained by privacy concerns, annotation costs, and organization-specific formats. We present , a semantic-first framework that uses a lightweight, task-specific ontology to generate enterprise form packets. The framework separates domain semantics from layout through ontology maps, hierarchical schemas, dependency-aware entity sampling, deterministic validation, and template bindings. It produces rendered forms with field boxes, ontology-keyed extraction targets, grounded question-answer pairs, and validation metadata. We instantiate the framework on three digitally rendered surrogate insurance form types, producing 706 forms. Finetuned vision-language models improve ontology-keyed extraction $F_1$ by 4.99 points and grounded-QA $ROUGE-L$ by 44.1 points over their zero-shot baselines. Ontology guidance further improves held-out-form extraction $F_1$ by 36.05 points overall and by 42.67 points on concepts absent from training, while increasing exact cross-form reasoning accuracy by 34.17 points. These results demonstrate the utility of the generated supervision signals for downstream tasks"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kunananthaseelan-etal-2026-ontoform">
<titleInfo>
<title>ONTOFORM: Ontology-Grounded Semantic Data Generation for Enterprise Document Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nilakshan</namePart>
<namePart type="family">Kunananthaseelan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Kane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahsa</namePart>
<namePart type="family">Ghorbanali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatemeh</namePart>
<namePart type="family">Shiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Tumuluri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</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 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Enterprise forms are layout-specific observations of real-world entities whose semantics span fields, recurring sections and related documents. Developing enterprise document-understanding systems requires large-scale supervision, but obtaining authentic forms is constrained by privacy concerns, annotation costs, and organization-specific formats. We present , a semantic-first framework that uses a lightweight, task-specific ontology to generate enterprise form packets. The framework separates domain semantics from layout through ontology maps, hierarchical schemas, dependency-aware entity sampling, deterministic validation, and template bindings. It produces rendered forms with field boxes, ontology-keyed extraction targets, grounded question-answer pairs, and validation metadata. We instantiate the framework on three digitally rendered surrogate insurance form types, producing 706 forms. Finetuned vision-language models improve ontology-keyed extraction F₁ by 4.99 points and grounded-QA ROUGE-L by 44.1 points over their zero-shot baselines. Ontology guidance further improves held-out-form extraction F₁ by 36.05 points overall and by 42.67 points on concepts absent from training, while increasing exact cross-form reasoning accuracy by 34.17 points. These results demonstrate the utility of the generated supervision signals for downstream tasks</abstract>
<identifier type="citekey">kunananthaseelan-etal-2026-ontoform</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.210/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3535</start>
<end>3543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ONTOFORM: Ontology-Grounded Semantic Data Generation for Enterprise Document Understanding
%A Kunananthaseelan, Nilakshan
%A Kane, Benjamin
%A Jain, Siddharth
%A Ghorbanali, Mahsa
%A Shiri, Fatemeh
%A Tumuluri, Raj
%A Haffari, Gholamreza
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F kunananthaseelan-etal-2026-ontoform
%X Enterprise forms are layout-specific observations of real-world entities whose semantics span fields, recurring sections and related documents. Developing enterprise document-understanding systems requires large-scale supervision, but obtaining authentic forms is constrained by privacy concerns, annotation costs, and organization-specific formats. We present , a semantic-first framework that uses a lightweight, task-specific ontology to generate enterprise form packets. The framework separates domain semantics from layout through ontology maps, hierarchical schemas, dependency-aware entity sampling, deterministic validation, and template bindings. It produces rendered forms with field boxes, ontology-keyed extraction targets, grounded question-answer pairs, and validation metadata. We instantiate the framework on three digitally rendered surrogate insurance form types, producing 706 forms. Finetuned vision-language models improve ontology-keyed extraction F₁ by 4.99 points and grounded-QA ROUGE-L by 44.1 points over their zero-shot baselines. Ontology guidance further improves held-out-form extraction F₁ by 36.05 points overall and by 42.67 points on concepts absent from training, while increasing exact cross-form reasoning accuracy by 34.17 points. These results demonstrate the utility of the generated supervision signals for downstream tasks
%U https://aclanthology.org/2026.emnlp-industry.210/
%P 3535-3543
Markdown (Informal)
[ONTOFORM: Ontology-Grounded Semantic Data Generation for Enterprise Document Understanding](https://aclanthology.org/2026.emnlp-industry.210/) (Kunananthaseelan et al., EMNLP 2026)
ACL