@inproceedings{stankovic-etal-2026-integrating,
title = "Integrating {TEI}, {NER}/{NEL}, Textometry, and Linked Data for a Semantically Enriched Interview Corpus",
author = "Stankovic, Ranka and
Vu{\v{c}}enovi{\'c}, Tamara and
Rujevi{\'c}, Biljana and
Ikoni{\'c} Ne{\v{s}}i{\'c}, Milica and
{\v{S}}kori{\'c}, Mihailo",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.114/",
doi = "10.63317/4zjef9ycsupk",
pages = "1474--1484",
abstract = "This paper presents a pipeline that converts unstructured interview transcripts into a semantically enriched, queryable knowledge resource. The texts from the \textit{Digitalne Ikone 20+} interview collection were first encoded in TEI XML (Text Encoding Initiative), marking interview boundaries, paragraph breaks, speaker turns with identifiers, dates, and topics. This structural encoding underpins downstream NLP and enables structured querying (e.g., by speaker). We then applied Named Entity Recognition to identify persons, places, organizations, and events, and embedded the results directly in TEI. In the third stage, Named Entity Linking mapped entity mentions to canonical Wikidata identifiers via context-aware disambiguation; missing entries were added to Wikidata when necessary. The resulting TEI+NER/NEL corpus, serialized as linked data, follows the NIF (NLP Interchange Framework). The pipeline also supports retrieval-augmented summarization that retrieves evidence passages and prompts LLMs (implemented with DSPy) to produce faithful interview summaries. We discuss design choices (TXM for textometry with JeRTeh resources; TESLA models for NER/NEL), report qualitative gains in interpretability through semantic links, and outline future work on domain-adapted NER/NEL, graph-based completion, and more expressive RAG architectures. The approach is replicable for other oral-history or media corpora and advances practical, evidence-grounded access to cultural archives and beyond."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stankovic-etal-2026-integrating">
<titleInfo>
<title>Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ranka</namePart>
<namePart type="family">Stankovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamara</namePart>
<namePart type="family">Vučenović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biljana</namePart>
<namePart type="family">Rujević</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Ikonić Nešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihailo</namePart>
<namePart type="family">Škorić</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a pipeline that converts unstructured interview transcripts into a semantically enriched, queryable knowledge resource. The texts from the Digitalne Ikone 20+ interview collection were first encoded in TEI XML (Text Encoding Initiative), marking interview boundaries, paragraph breaks, speaker turns with identifiers, dates, and topics. This structural encoding underpins downstream NLP and enables structured querying (e.g., by speaker). We then applied Named Entity Recognition to identify persons, places, organizations, and events, and embedded the results directly in TEI. In the third stage, Named Entity Linking mapped entity mentions to canonical Wikidata identifiers via context-aware disambiguation; missing entries were added to Wikidata when necessary. The resulting TEI+NER/NEL corpus, serialized as linked data, follows the NIF (NLP Interchange Framework). The pipeline also supports retrieval-augmented summarization that retrieves evidence passages and prompts LLMs (implemented with DSPy) to produce faithful interview summaries. We discuss design choices (TXM for textometry with JeRTeh resources; TESLA models for NER/NEL), report qualitative gains in interpretability through semantic links, and outline future work on domain-adapted NER/NEL, graph-based completion, and more expressive RAG architectures. The approach is replicable for other oral-history or media corpora and advances practical, evidence-grounded access to cultural archives and beyond.</abstract>
<identifier type="citekey">stankovic-etal-2026-integrating</identifier>
<identifier type="doi">10.63317/4zjef9ycsupk</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.114/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1474</start>
<end>1484</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus
%A Stankovic, Ranka
%A Vučenović, Tamara
%A Rujević, Biljana
%A Ikonić Nešić, Milica
%A Škorić, Mihailo
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F stankovic-etal-2026-integrating
%X This paper presents a pipeline that converts unstructured interview transcripts into a semantically enriched, queryable knowledge resource. The texts from the Digitalne Ikone 20+ interview collection were first encoded in TEI XML (Text Encoding Initiative), marking interview boundaries, paragraph breaks, speaker turns with identifiers, dates, and topics. This structural encoding underpins downstream NLP and enables structured querying (e.g., by speaker). We then applied Named Entity Recognition to identify persons, places, organizations, and events, and embedded the results directly in TEI. In the third stage, Named Entity Linking mapped entity mentions to canonical Wikidata identifiers via context-aware disambiguation; missing entries were added to Wikidata when necessary. The resulting TEI+NER/NEL corpus, serialized as linked data, follows the NIF (NLP Interchange Framework). The pipeline also supports retrieval-augmented summarization that retrieves evidence passages and prompts LLMs (implemented with DSPy) to produce faithful interview summaries. We discuss design choices (TXM for textometry with JeRTeh resources; TESLA models for NER/NEL), report qualitative gains in interpretability through semantic links, and outline future work on domain-adapted NER/NEL, graph-based completion, and more expressive RAG architectures. The approach is replicable for other oral-history or media corpora and advances practical, evidence-grounded access to cultural archives and beyond.
%R 10.63317/4zjef9ycsupk
%U https://aclanthology.org/2026.lrec-1.114/
%U https://doi.org/10.63317/4zjef9ycsupk
%P 1474-1484
Markdown (Informal)
[Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus](https://aclanthology.org/2026.lrec-1.114/) (Stankovic et al., LREC 2026)
ACL
- Ranka Stankovic, Tamara Vučenović, Biljana Rujević, Milica Ikonić Nešić, and Mihailo Škorić. 2026. Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1474–1484, Palma de Mallorca, Spain. ELRA Language Resource Association.