---
title: "Integrating TEI, NER/NEL, Textometry, and — Stankovic 2026"
description: "Interview and broadcast transcripts are difficult to search and analyse, especially in lower-resourced languages such as Serbian."
authors: ["Ranka Stankovic", "Tamara Vučenović", "Biljana Rujević", "Milica Ikonić Nešić", "Mihailo Škorić"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.114/"
doi: "10.63317/4zjef9ycsupk"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/stankovic-2026-integrating-tei-ner-nel-textometry/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/stankovic-2026-integrating-tei-ner-nel-textometry/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/) / Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus

# Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus

**Authors:** Ranka Stankovic, Tamara Vučenović, Biljana Rujević, Milica Ikonić Nešić, Mihailo Škorić · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.114/) · [PDF](https://aclanthology.org/2026.lrec-1.114.pdf) · [DOI 10.63317/4zjef9ycsupk](https://doi.org/10.63317/4zjef9ycsupk) · [OpenAlex](https://openalex.org/W7160174711)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
Interview and broadcast transcripts are difficult to search and analyse, especially in lower-resourced languages such as Serbian. The authors present a reusable, standards-based workflow that turns such material into a structured, linked knowledge resource. Their test case is DigIko, a corpus built from the book *Digital Icons 20+*, which collects transcripts of a long-running Radio Belgrade 2 programme on digital technology.

The workflow has several stages:
- **Structure:** transcripts are encoded in TEI XML, covering interviews, speaker turns, dates and topics.
- **Preprocessing and exploration:** TXM, together with JeRTeh resources, handles preprocessing and supports textometric exploration.
- **Entities:** TESLA models perform NER, and the annotations are stored inside the TEI. Mentions are then linked to Wikidata, with new items created when an entity was missing.
- **Linked data:** the enriched corpus is published as NIF.
- **Summarization:** a retrieval-augmented component built with DSPy feeds evidence passages to LLMs.

Evaluation is at pilot scale. NER handles the core entity types well, and location linking is precise. In summarizing long question–answer pairs, GPT-5 performed best among the systems compared. The work matters because it gives oral-history and media archives a replicable way to support speaker-aware, entity-aware, verifiable search and summarization.

## Key points
- **Source material:** the *Digital Icons* programme has aired since 2002 and has exceeded 1,000 episodes. The DigIko corpus is still modest in size, and the authors plan to expand it.
- **Tooling:** TEI/ODD for encoding; TXM, NoSketch and INCEpTION for curation and analysis; NIF with Fuseki for SPARQL access; DSPy for evidence-based prompting. The linked-data edition is hosted at https://llod.jerteh.rs/digiko/.
- **NER and NEL results:** PERS, ROLE and LOC are recognised reliably, while ORG, WORK and PRODUCT remain difficult. NEL for locations has high precision but weaker recall.
- **Summarization results:** quality was measured with ROUGE-L and BERTScore-F1 on question–answer pairs longer than 200 characters. GPT-5 outperformed GPT-4.1 and a Serbian baseline summarizer, with BERTScore-F1 values of 0.72, 0.69 and 0.63 across the three systems.
- **Planned work:**
  - release the NER+NEL models and TEI/NIF samples;
  - extend linking beyond locations through domain adaptation;
  - make retrieval speaker-aware and entity-aware;
  - enlarge the SD1 dataset and retrain the SM1 summarizer.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{stankovic2026integrating,
  title = {{Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus}},
  author = {Stankovic, Ranka and Vučenović, Tamara and Rujević, Biljana and Nešić, Milica Ikonić and Škorić, Mihailo},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/4zjef9ycsupk},
  url = {https://doi.org/10.63317/4zjef9ycsupk}
}
```

- [← previous Integrating Services, Platforms and Resources into a National Infrastructure Cluster for FAIR Language and Cultural Data](https://md.research.elamur.ai/free/en/papers/pedonese-2026-integrating-services-platforms-resources-into/)
- [next → Interaction in Biblical Hebrew Narrative: A Conversation-Analytic Approach](https://md.research.elamur.ai/free/en/papers/hbo-2026-patty-interaction-biblical-hebrew-narrative-conversation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/)

## References

33 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Robin Camille Davis. 2015. Synchronizing Oral History Text and Speech: a Tools Overview. Behavioral & Social Sciences Librarian, 34(4):234– 238. [find](https://scholar.google.com/scholar?q=Robin+Camille+Davis%2E+2015%2E+Synchronizing+Oral+History+Text+and+Speech%3A+a+Tools+Overview%2E+Behavioral+%26+Social+Sciences+Librarian%2C+34%284%29%3A234%E2%80%93+238%2E)
2. Bernhard Fisseni and Thomas Schmidt. 2019. CLARIN Web Services for TEI-annotated Transcripts of Spoken Language. In Selected Papers from the CLARIN Annual Conference 2019. Leipzig, 30 September-2 October 2019, pages 12–22. Linköping University Electronic Press. [find](https://scholar.google.com/scholar?q=Bernhard+Fisseni+and+Thomas+Schmidt%2E+2019%2E+CLARIN+Web+Services+for+TEI%2Dannotated+Transcripts+of+Spoken+Language%2E+In+Selected+Papers+from+the+CLARIN+Annual+Conference+2019%2E+Leipzig%2C+30+September%2D2+Octo)
3. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv preprint arXiv:2312.10997, 2(1). [find](https://scholar.google.com/scholar?q=Yunfan+Gao%2C+Yun+Xiong%2C+Xinyu+Gao%2C+Kangxiang+Jia%2C+Jinliu+Pan%2C+Yuxi+Bi%2C+Yixin+Dai%2C+Jiawei+Sun%2C+Haofen+Wang%2C+and+Haofen+Wang%2E+2023%2E+Retrieval%2DAugmented+Generation+for+Large+Language+Models%3A+A+Survey%2E+arX) [our card](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/)
4. Serge Heiden. 2010. The TXM Platform: Building Open-Source Textual Analysis Software Compatible with the TEI Encoding Scheme. In 24th Pacific Asia Conference on Language, Information and Computation, volume 2, pages 389–-398, Japan. [find](https://scholar.google.com/scholar?q=Serge+Heiden%2E+2010%2E+The+TXM+Platform%3A+Building+Open%2DSource+Textual+Analysis+Software+Compatible+with+the+TEI+Encoding+Scheme%2E+In+24th+Pacific+Asia+Conference+on+Language%2C+Information+and+Computation%2C+)
5. Serge Heiden, Bénédicte Pincemin, and Matthieu Decorde. 2015. Manuel de TXM. Manuel d’utilisation du logiciel TXM. [find](https://scholar.google.com/scholar?q=Serge+Heiden%2C+B%C3%A9n%C3%A9dicte+Pincemin%2C+and+Matthieu+Decorde%2E+2015%2E+Manuel+de+TXM%2E+Manuel+d%E2%80%99utilisation+du+logiciel+TXM%2E)
6. Gautier Izacard and Edouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. In Proceedings of the 16th Conference of the European Chapter of the ACL: Main Volume, pages 874–880, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Gautier+Izacard+and+Edouard+Grave%2E+2021%2E+Leveraging+Passage+Retrieval+with+Generative+Models+for+Open+Domain+Question+Answering%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+of+the+AC) [our card](https://md.research.elamur.ai/free/en/papers/izacard-2021-leveraging-passage-retrieval-generative-models/)
7. Omar Khattab, Arnav Singhvi, and et al. 2024. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Omar+Khattab%2C+Arnav+Singhvi%2C+and+et+al%2E+2024%2E+DSPy%3A+Compiling+Declarative+Language+Model+Calls+into+Self%2DImproving+Pipelines%2E+In+Proceedings+of+the+Twelfth+International+Conference+on+Learning+Represe) [our card](https://md.research.elamur.ai/free/en/papers/khattab-2023-dspy-compiling-declarative-language-model/)
8. Cvetana Krstev, Jelena Jaćimović, Branislava Šandrih, and Ranka Stanković. 2019. Analysis of the First Serbian Literature Corpus of the Late 19 th and Early 20 th Century with the TXM Platform. In DH_BUDAPEST_2019, pages 36–37. Centre for Digital Humanities - Eötvös Loránd University. [find](https://scholar.google.com/scholar?q=Cvetana+Krstev%2C+Jelena+Ja%C4%87imovi%C4%87%2C+Branislava+%C5%A0andrih%2C+and+Ranka+Stankovi%C4%87%2E+2019%2E+Analysis+of+the+First+Serbian+Literature+Corpus+of+the+Late+19+th+and+Early+20+th+Century+with+the+TXM+Platform%2E+In+DH%5F)
9. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Karpukhin, et al. 2020. Retrieval-Augmented Generation for Knowledge-intensive NLP Tasks. Advances in neural information processing systems, 33:9459–9474. [find](https://scholar.google.com/scholar?q=Patrick+Lewis%2C+Ethan+Perez%2C+Aleksandra+Piktus%2C+Fabio+Petroni%2C+Karpukhin%2C+et+al%2E+2020%2E+Retrieval%2DAugmented+Generation+for+Knowledge%2Dintensive+NLP+Tasks%2E+Advances+in+neural+information+processing+system)
10. Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text summarization branches out, pages 74–81. [find](https://scholar.google.com/scholar?q=Chin%2DYew+Lin%2E+2004%2E+ROUGE%3A+A+Package+for+Automatic+Evaluation+of+Summaries%2E+In+Text+summarization+branches+out%2C+pages+74%E2%80%9381%2E)
11. Milica Ikonić Nešić, Ranka Stanković, Christof Schöch, and Mihailo Škorić. 2022. From ELTeC Text Collection Metadata and Named Entities to Linked-data (and Back). In Proceedings of the 8th Workshop on Linked Data in Linguistics within the 13th Language Resources and Evaluation Conference, pages 7–16… [find](https://scholar.google.com/scholar?q=Milica+Ikoni%C4%87+Ne%C5%A1i%C4%87%2C+Ranka+Stankovi%C4%87%2C+Christof+Sch%C3%B6ch%2C+and+Mihailo+%C5%A0kori%C4%87%2E+2022%2E+From+ELTeC+Text+Collection+Metadata+and+Named+Entities+to+Linked%2Ddata+%28and+Back%29%2E+In+Proceedings+of+the+8th+Workshop+on)
12. Marie Puren and Florian Cafiero. 2024. InTEIrviews: An ODD for Qualitative Interviews in the Humanities. Journal of the Text Encoding Initiative, 2024(15). [find](https://scholar.google.com/scholar?q=Marie+Puren+and+Florian+Cafiero%2E+2024%2E+InTEIrviews%3A+An+ODD+for+Qualitative+Interviews+in+the+Humanities%2E+Journal+of+the+Text+Encoding+Initiative%2C+2024%2815%29%2E)
13. Ranka Stanković, Cvetana Krstev, Branislava Šandrih Todorović, Duško Vitas, Mihailo Škoric, and Milica Ikonić Nešić. 2022. Distant Reading in Digital Humanities: Case Study on the Serbian Part of the ELTeC Collection. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pag… [find](https://scholar.google.com/scholar?q=Ranka+Stankovi%C4%87%2C+Cvetana+Krstev%2C+Branislava+%C5%A0andrih+Todorovi%C4%87%2C+Du%C5%A1ko+Vitas%2C+Mihailo+%C5%A0koric%2C+and+Milica+Ikoni%C4%87+Ne%C5%A1i%C4%87%2E+2022%2E+Distant+Reading+in+Digital+Humanities%3A+Case+Study+on+the+Serbian+Part+of+the+)
14. Ranka Stanković, Cvetana Krstev, and Duško Vitas. 2024. Srpeltec: A serbian literary corpus for distant reading. Primerjalna književnost, 47(2):45– 63. [find](https://scholar.google.com/scholar?q=Ranka+Stankovi%C4%87%2C+Cvetana+Krstev%2C+and+Du%C5%A1ko+Vitas%2E+2024%2E+Srpeltec%3A+A+serbian+literary+corpus+for+distant+reading%2E+Primerjalna+knji%C5%BEevnost%2C+47%282%29%3A45%E2%80%93+63%2E)
15. Ranka Stanković, Branislava Sandrih, Cvetana Krstev, Miloš Utvić, and Mihailo Škorić. 2020. Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian. In LREC 2020-12th International Conference on Language Resources and Evaluation, Conference Proceedings, p… [find](https://scholar.google.com/scholar?q=Ranka+Stankovi%C4%87%2C+Branislava+Sandrih%2C+Cvetana+Krstev%2C+Milo%C5%A1+Utvi%C4%87%2C+and+Mihailo+%C5%A0kori%C4%87%2E+2020%2E+Machine+Learning+and+Deep+Neural+Network%2DBased+Lemmatization+and+Morphosyntactic+Tagging+for+Serbian%2E+In+LRE)
16. TEI Consortium. 2025a. Linking, segmentation, and alignment. In TEI P5: Guidelines for Electronic Text Encoding and Interchange, version 4.10.2 edition. TEI Consortium. See §17.2.4 TEI XPointer Schemes (profile/pointer mechanisms relevant to transcribed speech). [find](https://scholar.google.com/scholar?q=TEI+Consortium%2E+2025a%2E+Linking%2C+segmentation%2C+and+alignment%2E+In+TEI+P5%3A+Guidelines+for+Electronic+Text+Encoding+and+Interchange%2C+version+4%2E10%2E2+edition%2E+TEI+Consortium%2E+See+%C2%A717%2E2%2E4+TEI+XPointer+Scheme)
17. TEI Consortium. 2025b. The TEI Header. In TEI P5: Guidelines for Electronic Text Encoding and Interchange, version 4.10.2 edition. TEI Consortium. Last updated 4 Sept 2025. [find](https://scholar.google.com/scholar?q=TEI+Consortium%2E+2025b%2E+The+TEI+Header%2E+In+TEI+P5%3A+Guidelines+for+Electronic+Text+Encoding+and+Interchange%2C+version+4%2E10%2E2+edition%2E+TEI+Consortium%2E+Last+updated+4+Sept+2025%2E)
18. TEI Consortium. 2025c. Transcriptions of Speech. In TEI P5: Guidelines for Electronic Text Encoding and Interchange, version 4.10.2 edition. TEI Consortium. Last updated 4 Sept 2025. [find](https://scholar.google.com/scholar?q=TEI+Consortium%2E+2025c%2E+Transcriptions+of+Speech%2E+In+TEI+P5%3A+Guidelines+for+Electronic+Text+Encoding+and+Interchange%2C+version+4%2E10%2E2+edition%2E+TEI+Consortium%2E+Last+updated+4+Sept+2025%2E)
19. Darinka Verdonik, Kaja Dobrovoljc, Tomaž Erjavec, and Nikola Ljubešić. 2024. Gos 2: A New Reference Corpus of Spoken Slovenian. In Proceedings of LREC-COLING 2024, pages 7825–7830. [find](https://scholar.google.com/scholar?q=Darinka+Verdonik%2C+Kaja+Dobrovoljc%2C+Toma%C5%BE+Erjavec%2C+and+Nikola+Ljube%C5%A1i%C4%87%2E+2024%2E+Gos+2%3A+A+New+Reference+Corpus+of+Spoken+Slovenian%2E+In+Proceedings+of+LREC%2DCOLING+2024%2C+pages+7825%E2%80%937830%2E)
20. Tamara Vučenović. 2024. Digitalne ikone 20+ [Digital Icons 20+]. Akademska knjiga; Radio Televizija Beograd - RTS. [find](https://scholar.google.com/scholar?q=Tamara+Vu%C4%8Denovi%C4%87%2E+2024%2E+Digitalne+ikone+20%2B+%5BDigital+Icons+20%2B%5D%2E+Akademska+knjiga%3B+Radio+Televizija+Beograd+%2D+RTS%2E)
21. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. BERTScore: Evaluating Text Generation with BERT. arXiv preprint arXiv:1904.09675, page 43. 10. [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2C+Varsha+Kishore%2C+Felix+Wu%2C+Kilian+Q+Weinberger%2C+and+Yoav+Artzi%2E+2019%2E+BERTScore%3A+Evaluating+Text+Generation+with+BERT%2E+arXiv+preprint+arXiv%3A1904%2E09675%2C+page+43%2E+10%2E)
22. Language Resource References Apache Software Foundation, Apache. 2023. Apache Jena Fuseki. The Apache Software Foundation, [https://jena.apache.org/documentation/fuseki2/](https://jena.apache.org/documentation/fuseki2/). [↗](https://jena.apache.org/documentation/fuseki2/)
23. Klie, Jan-Christoph and Bugert, Michael and Boullosa, Beto and Eckart de Castilho, Richard and Gurevych, Iryna. 2018. The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation. Association for Computational Linguistics, [https://inception-project.github.io](https://inception-project.github.io). [↗](https://inception-project.github.io) [our card](https://md.research.elamur.ai/free/en/papers/klie-2018-inception-platform-machine-assisted-knowledge/)
24. Cvetana Krstev and Branislava Šandrih Todorović and Ranka Stanković and Milica Ikonić Nešić. 2021. SrpELTeC-gold - Named Entity Recognition Training Corpus for Serbian. ELG, [https://live.european-language-grid.eu/](https://live.european-language-grid.eu/) catalogue/corpus/9485, 1.0. [↗](https://live.european-language-grid.eu/)
25. OpenAI. 2024. GPT-4.1: OpenAI Large Language Model. OpenAI. OpenAI. Accessed via OpenAI API on 2025-10-15. Model version: gpt-4.1. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+GPT%2D4%2E1%3A+OpenAI+Large+Language+Model%2E+OpenAI%2E+OpenAI%2E+Accessed+via+OpenAI+API+on+2025%2D10%2D15%2E+Model+version%3A+gpt%2D4%2E1%2E)
26. OpenAI. 2025. GPT-5: OpenAI Large Language Model. OpenAI. OpenAI. Accessed via OpenAI API on 2025-10-15. Model version: gpt-5. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+GPT%2D5%3A+OpenAI+Large+Language+Model%2E+OpenAI%2E+OpenAI%2E+Accessed+via+OpenAI+API+on+2025%2D10%2D15%2E+Model+version%3A+gpt%2D5%2E)
27. Ranka Stanković and Tamara Vučenović. 2026. DigIko: Digital Icons 20+ – TEI Interview Corpus Annotated with Named Entities and Linked to Wikidata. TESLA Project, Science Fund of the Republic of Serbia \#7276. Hugging Face. [find](https://scholar.google.com/scholar?q=Ranka+Stankovi%C4%87+and+Tamara+Vu%C4%8Denovi%C4%87%2E+2026%2E+DigIko%3A+Digital+Icons+20%2B+%E2%80%93+TEI+Interview+Corpus+Annotated+with+Named+Entities+and+Linked+to+Wikidata%2E+TESLA+Project%2C+Science+Fund+of+the+Republic+of+Serbia)
28. Heiden Serge. 2020. The TXM Platform. Equipe TXM, [https://txm.gitpages.huma-num.fr/textometrie/](https://txm.gitpages.huma-num.fr/textometrie/). [↗](https://txm.gitpages.huma-num.fr/textometrie/)
29. Mihailo Škorić. 2025. TeslaXLM: Multilingual Transformer for Serbian (te-sla/TeslaXLM). TESLA Project, Science Fund of the Republic of Serbia \#7276. HugginFace. Hugging Face model card; base-model: XLM-R; license: CC-BY-SA-4.0. [find](https://scholar.google.com/scholar?q=Mihailo+%C5%A0kori%C4%87%2E+2025%2E+TeslaXLM%3A+Multilingual+Transformer+for+Serbian+%28te%2Dsla%2FTeslaXLM%29%2E+TESLA+Project%2C+Science+Fund+of+the+Republic+of+Serbia+%5C%237276%2E+HugginFace%2E+Hugging+Face+model+card%3B+base%2Dmodel%3A+X)
30. Stanford NLP. 2025. DSPy: The framework for programming—not prompting—language models. Stanford NLP Group. Version 3.0.3, MIT License. [find](https://scholar.google.com/scholar?q=Stanford+NLP%2E+2025%2E+DSPy%3A+The+framework+for+programming%E2%80%94not+prompting%E2%80%94language+models%2E+Stanford+NLP+Group%2E+Version+3%2E0%2E3%2C+MIT+License%2E)
31. Wikimedia. 2023. Wikidata. Wikimedia, [https://www.wikidata.org/](https://www.wikidata.org/). [↗](https://www.wikidata.org/)
32. Škorić, Mihailo and Stanković, Ranka. 2025. TE-SLA/Sumarizacija: A Serbian summarization dataset. Dataset hosted on Hugging Face Hub. [find](https://scholar.google.com/scholar?q=%C5%A0kori%C4%87%2C+Mihailo+and+Stankovi%C4%87%2C+Ranka%2E+2025%2E+TE%2DSLA%2FSumarizacija%3A+A+Serbian+summarization+dataset%2E+Dataset+hosted+on+Hugging+Face+Hub%2E)
33. Škorić, Mihailo and TESLA Team. 2025. PiloT5 – Serbian Summarization Model (te-sla/pilot5-sumarizacija). TESLA Project, Science Fund of the Republic of Serbia (\#7276). Hugging Face Model Card. License: CC-BY-4.0. [find](https://scholar.google.com/scholar?q=%C5%A0kori%C4%87%2C+Mihailo+and+TESLA+Team%2E+2025%2E+PiloT5+%E2%80%93+Serbian+Summarization+Model+%28te%2Dsla%2Fpilot5%2Dsumarizacija%29%2E+TESLA+Project%2C+Science+Fund+of+the+Republic+of+Serbia+%28%5C%237276%29%2E+Hugging+Face+Model+Card%2E+Licens)