@inproceedings{tamrazyan-etal-2026-corpus-concept,
title = "From Corpus to Concept Scheme: Developing a {SKOS} Vocabulary for {A}rmenian Epigraphic Heritage",
author = "Tamrazyan, Hamest and
Nour, Kamal and
Boros, Emanuela",
editor = "Alves, Diego and
Bizzoni, Yuri and
Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Pagel, Janis and
Szpakowicz, Stan",
booktitle = "Proceedings of the 10th Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.latechclfl-1.1/",
pages = "1--10",
ISBN = "979-8-89176-373-9",
abstract = "Armenian epigraphy, one of the world{'}s oldest and most diverse inscriptional traditions, remains largely absent from digital research infrastructures due to a lack of basic linguistic and conceptual resources. No machine-readable corpus, standardized terminology, or controlled vocabulary exists for describing Armenian inscription types, preventing indexing and interoperability. This paper addresses this gap by constructing the first dataset of Armenian inscription-type terminology and by developing a computational pipeline for analyzing it at scale. We digitize and preprocess a broad corpus of authoritative printed publications; curate a culturally grounded terminology list; and train transformer-based NER models to identify both attested inscription types and potential terminological variants across unseen texts. The resulting resources form the first empirical foundation for modelling Armenian epigraphic concepts needed for further developing a SKOS vocabulary aligned with, yet culturally distinct from, existing international epigraphic ontologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tamrazyan-etal-2026-corpus-concept">
<titleInfo>
<title>From Corpus to Concept Scheme: Developing a SKOS Vocabulary for Armenian Epigraphic Heritage</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamest</namePart>
<namePart type="family">Tamrazyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kamal</namePart>
<namePart type="family">Nour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emanuela</namePart>
<namePart type="family">Boros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janis</namePart>
<namePart type="family">Pagel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-373-9</identifier>
</relatedItem>
<abstract>Armenian epigraphy, one of the world’s oldest and most diverse inscriptional traditions, remains largely absent from digital research infrastructures due to a lack of basic linguistic and conceptual resources. No machine-readable corpus, standardized terminology, or controlled vocabulary exists for describing Armenian inscription types, preventing indexing and interoperability. This paper addresses this gap by constructing the first dataset of Armenian inscription-type terminology and by developing a computational pipeline for analyzing it at scale. We digitize and preprocess a broad corpus of authoritative printed publications; curate a culturally grounded terminology list; and train transformer-based NER models to identify both attested inscription types and potential terminological variants across unseen texts. The resulting resources form the first empirical foundation for modelling Armenian epigraphic concepts needed for further developing a SKOS vocabulary aligned with, yet culturally distinct from, existing international epigraphic ontologies.</abstract>
<identifier type="citekey">tamrazyan-etal-2026-corpus-concept</identifier>
<location>
<url>https://aclanthology.org/2026.latechclfl-1.1/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Corpus to Concept Scheme: Developing a SKOS Vocabulary for Armenian Epigraphic Heritage
%A Tamrazyan, Hamest
%A Nour, Kamal
%A Boros, Emanuela
%Y Alves, Diego
%Y Bizzoni, Yuri
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Pagel, Janis
%Y Szpakowicz, Stan
%S Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-373-9
%F tamrazyan-etal-2026-corpus-concept
%X Armenian epigraphy, one of the world’s oldest and most diverse inscriptional traditions, remains largely absent from digital research infrastructures due to a lack of basic linguistic and conceptual resources. No machine-readable corpus, standardized terminology, or controlled vocabulary exists for describing Armenian inscription types, preventing indexing and interoperability. This paper addresses this gap by constructing the first dataset of Armenian inscription-type terminology and by developing a computational pipeline for analyzing it at scale. We digitize and preprocess a broad corpus of authoritative printed publications; curate a culturally grounded terminology list; and train transformer-based NER models to identify both attested inscription types and potential terminological variants across unseen texts. The resulting resources form the first empirical foundation for modelling Armenian epigraphic concepts needed for further developing a SKOS vocabulary aligned with, yet culturally distinct from, existing international epigraphic ontologies.
%U https://aclanthology.org/2026.latechclfl-1.1/
%P 1-10
Markdown (Informal)
[From Corpus to Concept Scheme: Developing a SKOS Vocabulary for Armenian Epigraphic Heritage](https://aclanthology.org/2026.latechclfl-1.1/) (Tamrazyan et al., LaTeCH-CLfL 2026)
ACL