@inproceedings{del-grosso-etal-2026-integrating,
title = "Integrating {TEI} Publication, Guided Exploration, and Vector Databases for Semantic Search in the Voci dall{'}Inferno Project",
author = "Del Grosso, Angelo Mario and
Mercatanti, Elvira and
Congiu, Carla and
Riccucci, Marina",
editor = "Anuradha, Isuri and
Wynne, Martin",
booktitle = "Proceedings of The Second Workshop on Holocaust Testimonies as Language Resources ({HTR}es)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.htres-2.1/",
doi = "10.63317/2axve8uynrdb",
pages = "1--11",
abstract = "This paper presents recent advances toward an integrated framework that combines TEI-based digital publishing with embedding-based semantic search to support the preservation, exploration and analysis of Holocaust survivor testimonies. The corpus includes written and oral sources and preserves them within a XML-TEI model supported by an ODD customization that preserves provenance, structure and interpretability. A dedicated web application developed within the eXistdb platform provides guided access to the digital corpus and supports the management, visualization, and exploration of the encoded data. The project aims to investigate a specific research goal: to verify the presence of references to the Divine Comedy by Dante within Holocaust testimonies. To this end, we implement a semantic retrieval component based on SentenceTransformers' embeddings and a vector database, enabling the discovery of both literal and non-literal Dantean passages within the testimonies. The paper presents the advances achieved toward this objective and the ethical constraints shaping access policies, resulting in a sustainable archive and a reproducible methodology for intertextual research in sensitive historical collections."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="del-grosso-etal-2026-integrating">
<titleInfo>
<title>Integrating TEI Publication, Guided Exploration, and Vector Databases for Semantic Search in the Voci dall’Inferno Project</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angelo</namePart>
<namePart type="given">Mario</namePart>
<namePart type="family">Del Grosso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elvira</namePart>
<namePart type="family">Mercatanti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Congiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Riccucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Second Workshop on Holocaust Testimonies as Language Resources (HTRes)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isuri</namePart>
<namePart type="family">Anuradha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Wynne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents recent advances toward an integrated framework that combines TEI-based digital publishing with embedding-based semantic search to support the preservation, exploration and analysis of Holocaust survivor testimonies. The corpus includes written and oral sources and preserves them within a XML-TEI model supported by an ODD customization that preserves provenance, structure and interpretability. A dedicated web application developed within the eXistdb platform provides guided access to the digital corpus and supports the management, visualization, and exploration of the encoded data. The project aims to investigate a specific research goal: to verify the presence of references to the Divine Comedy by Dante within Holocaust testimonies. To this end, we implement a semantic retrieval component based on SentenceTransformers’ embeddings and a vector database, enabling the discovery of both literal and non-literal Dantean passages within the testimonies. The paper presents the advances achieved toward this objective and the ethical constraints shaping access policies, resulting in a sustainable archive and a reproducible methodology for intertextual research in sensitive historical collections.</abstract>
<identifier type="citekey">del-grosso-etal-2026-integrating</identifier>
<identifier type="doi">10.63317/2axve8uynrdb</identifier>
<location>
<url>https://aclanthology.org/2026.htres-2.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Integrating TEI Publication, Guided Exploration, and Vector Databases for Semantic Search in the Voci dall’Inferno Project
%A Del Grosso, Angelo Mario
%A Mercatanti, Elvira
%A Congiu, Carla
%A Riccucci, Marina
%Y Anuradha, Isuri
%Y Wynne, Martin
%S Proceedings of The Second Workshop on Holocaust Testimonies as Language Resources (HTRes)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F del-grosso-etal-2026-integrating
%X This paper presents recent advances toward an integrated framework that combines TEI-based digital publishing with embedding-based semantic search to support the preservation, exploration and analysis of Holocaust survivor testimonies. The corpus includes written and oral sources and preserves them within a XML-TEI model supported by an ODD customization that preserves provenance, structure and interpretability. A dedicated web application developed within the eXistdb platform provides guided access to the digital corpus and supports the management, visualization, and exploration of the encoded data. The project aims to investigate a specific research goal: to verify the presence of references to the Divine Comedy by Dante within Holocaust testimonies. To this end, we implement a semantic retrieval component based on SentenceTransformers’ embeddings and a vector database, enabling the discovery of both literal and non-literal Dantean passages within the testimonies. The paper presents the advances achieved toward this objective and the ethical constraints shaping access policies, resulting in a sustainable archive and a reproducible methodology for intertextual research in sensitive historical collections.
%R 10.63317/2axve8uynrdb
%U https://aclanthology.org/2026.htres-2.1/
%U https://doi.org/10.63317/2axve8uynrdb
%P 1-11
Markdown (Informal)
[Integrating TEI Publication, Guided Exploration, and Vector Databases for Semantic Search in the Voci dall’Inferno Project](https://aclanthology.org/2026.htres-2.1/) (Del Grosso et al., htres 2026)
ACL