Četrtek / Thursday, 17. 9. 2026
Program in urnik konference JT-DH 2026. Iskalno okence ob posameznem urniku omogoča iskanje posameznih sekcij, predstavitev ali avtorjev.
/
Program and timetable for the JT-DH 2026 conference. The search box next to each timetable allows you to search for specific sessions, presentations, or authors.
Četrtek / Thursday, 17. 9. 2026
| Ura / Time | Sekcija / Section | Predstavitve / Presentations | Paralelna sekcija / Parallel section | ||
|---|---|---|---|---|---|
| 08.30– | Registracija odprta | ||||
| 9:00–9:20 | Pozdravi in začetek konference | ||||
| 09.20–10.20 | Invited Talk / Vabljeno predavanje (in English) | Section Chair / Vodja sekcije: | |||
| Andrea Kocsis | Digital Ghosts: Communicating Absence, Loss, and Uncertainty in Humanities Data | ||||
| 10.20–10.40 | Coffee Break / Odmor za kavo | ||||
| 10.40–12.00 | Section 1 / Sekcija 1: Society, Memory and Cultural Data / Družba, spomin in kulturni podatki (in English) | Section Chair / Vodja sekcije: | |||
| 10:40–11:00 | Katja Meden, Tamara Logar, Gustavo Candela, Paul Spence & Andrej Pančur | Exploring the Enrichment of the Database of Fatalities of the Second World War in Slovenia: A Collections as Data approach | |||
| 11:00–11:20 | Filip Dobranić & Matevž Pesek | Commerce in Columns: Automated Detection and Corpus Construction for Advertisements in Slovenski narod from 1868 to 1914 | |||
| 11:20–11:40 | Tina Munda, Oliver Pejić, Vojko Gorjanc, Uroš Šmajdek, Filip Dobranić & Darja Fišer | Evaluative Framing of Collective Identities in Leading Slovene Newspapers from the Late Habsburg Empire | |||
| 11:40–12:00 | Rebeka Kropivšek Leskovar, Polona Tratnik, Antoine Doucet & Marko Robnik-Šikonja | Identifying Hero Types in Folk Tales Using Large Language Models | |||
| 12.00–13.15 | Lunch, Coffee and Poster Session / Kosilo, kava in predstavitev plakatov | ||||
| Aleš Vaupotič & Narvika Bovcon | Trajnostna digitalna hramba novomedijske umetnosti in dostopnost podatkov v paradigmi odprte znanosti: orodje Digitalni depo | ||||
| Karim El Haff & Polona Tratnik | Annotating the Outlaw-Hero: Evaluating Large Language Models on a Folkloristic Classification Task | ||||
| Ivan Porupski & Nikola Ljubešić | Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments | ||||
| Massimo Sbarbaro & Damjan Popič | Beyond Span Detection: Comparing NER Approaches for Medieval Patronymics in the Thesaurus Ecclesiae Aquileiensis | ||||
| Ajda Pretnar Žagar, Vojko Gorjanc & Matija Marolt | Tracking Lexical Semantic Change in Historical Slovenian Corpora with Contextual Embeddings | ||||
| Jasna Vidinić & Karlo Crnek | Automatic Sentiment Annotation and Analysis of Texts on Slovenian Independence in Mladika (1980–1990) | ||||
| Tina Munda & Špela Arhar Holdt | Na poti k skladenjskemu poenostavljanju pravnih besedil: Od metrik do mejnih vrednosti | ||||
| Neja Blaj Hribar, Vid Klopčič & Andrej Pančur | From Transcription to Platform: A New Tool for Managing Historical Census Data on the SIstory Portal | ||||
| Živa Štebljaj, Tina Munda, Špela Arhar Holdt, Nejc Robida, Polona Gantar & Marko Robnik-Šikonja | Strojno podprta kontrola kakovosti pri pripravi učnih podatkov za slovnično pregledovanje | ||||
| Vojko Gorjanc & Matej Klemen | Razvoj korpusa lahkega branja v slovenščini za poenostavljanje besedil z umetno inteligenco | ||||
| Ksenija Bogetić & Nikola Ljubešić | Generative AI for Corpus-Assisted Discourse Studies in ‘Low-Resource’ Languages: A Qualitative Assessment of ChatGPT in the Analysis of an Emerging ‘Anti-Genderist’ Right-Wing Term | ||||
| Jan Kostanjevec | A Formalism in Several Framings? Explicating −logp(x) in Machine Learning | ||||
| 13:15–14:30 | Section 2 / Sekcija 2: Student Section / Študentska sekcija (in English and Slovene) | Section Chairs / Vodji sekcije: Tjaša Arčon & Tina Munda | 13:15–14:30 | Sekcija DiPaDA / Session DiPaDA: Digital Parliamentary Data in Action (in English) | Section Chair / Vodja sekcije: Ajda Pretnar Žagar |
| 13:15–13:30 | Lea Vodopivec & Pia Polutnik | Detecting and Correcting Noisy Labels in Slovenian Sentiment Datasets: Effects on GaMS-2B Model Performance | 13:15-13:45 | Riccardo Graziani & Jakob Vanschoonbeek | Who Speaks for the People? Electoral Reforms, Parliamentary Speech, And Legislative Behavior in Belgium, 1880–1912 |
| 13:30–13:45 | Pia Polutnik & Lea Vodopivec | Translation of Idioms in Large Language Models and Machine Translation Tools from English to Slovene | |||
| 13:45–14:00 | Nives Hüll | A Community in Formation: Corpus Construction and Initial Analysis of Slovene Posts on Bluesky | 13:45-14:00 | Ajda Pretnar Žagar | Between Procedure and Representation: Constituency Effects in the Carniolan Provincial Assembly (1861-1913) |
| 14:00–14:15 | Milica Savić | The Languages of Archaeology Online: A Comparative Analysis of South Slavic CLASSLA-Web Corpora | 14:00-14:30 | Anna Kryvenko | Metaphorising European Integration in Ukrainian Parliamentary Discourse: A Longitudinal Corpus-Assisted Study |
| 14:15–14:30 | Nina Sangawa Hmeljak | Označevanje tonemskega naglasa v učnem slovarju japonščine | |||
| 14:30–14:40 | Coffee Break / Odmor za kavo | ||||
| 14:40–16:20 | Section 3 / Sekcija 3: Corpus-Based and Computational Methods / Korpusne in računalniške metode (in English) | Section Chair / Vodja sekcije: | |||
| 14:40–15:00 | Isabell Furkert & Nikola Ljubešić | Constructing Immigration in Parliament: A Multi-Stage Corpus-Linguistic Pipeline for Comparative Discourse Analysis | |||
| 15:00–15:20 | Jože Fortun & Matija Marolt | Uporaba s poizvedovanjem obogatenega generiranja za iskanje po zgodovinskih parlamentarnih korpusih | |||
| 15:20–15:40 | Jakob Lenardič & Kaja Dobrovoljc Zor | Exploring Syntactically Parsed Corpora in Slovenian with CLARIN.SI's noSketch Engine | |||
| 15:40–16:00 | Uroš Šmajdek, Tina Munda & Matija Marolt | Low-Resource Historical Named Entity Recognition in the Era of Large Language Models | |||
| 16:00–16:20 | Domagoj Pinčić & Martina Bajčić | Challenges of The Legal Translation Task in the Context of Machine Learning | |||
| 16:20–16:30 | Coffee Break / Odmor za kavo | ||||
| 16.30–18.00 | Panel | ||||
| 19:00–21:00 | Conference Dinner / Konferenčna večerja |
Petek / Friday, 18. 9. 2026
| Ura / Time | Sekcija / Section | Predstavitve / Presentations |
|---|---|---|
| 08.30– | Registracija odprta | |
| 09.00–10.00 | Invited Talk / Vabljeno predavanje (in English) | Section chair / Vodja sekcije: |
| Anna Vacalopoulou | LLMs as Lexicographers: Who Needs Dictionaries When AI Knows Everything? | |
| 10.00–10.20 | Coffee Break / Odmor za kavo | |
| 10.20–12.00 | Section 4 / Sekcija 4: Model Performance, Transfer and Bias / Zmogljivost, prenos in pristranskosti modelov (in English) | Section Chair / Vodja sekcije: |
| 10:20–10:40 | Luka Terčon & Kaja Dobrovoljc Zor | Evaluating the Linguistic Characteristics of the GaMS Large Language Model in Slovenian |
| 10:40–11:00 | Luka Debevc & Matej Martinc | Lost in Translation or Found in Ideology? A Robust Statistical Assessment of Political Bias and Steerability in Slovenian Large Language Models |
| 11:00–11:20 | Milica Cvetković, Aleksandra Todorović, Vuk Batanović & Boško Nikolić | Gender Bias in Named Entity Recognition Models for Serbian – an Initial Study |
| 11:20–11:40 | Nikola Ivačič, Senja Pollak, Jaya Caporusso, Matthew Purver & Nada Lavrač | When Is Multilingual Transfer Beneficial for Slavic Named Entity Recognition? |
| 11:40–12:00 | Federico Di Pasqua | Pedagogical Questions as Domain Benchmarks: Evaluating Retrieval-Augmented Generation for Classical Antiquity |
| 12.00–13:15 | Lunch, Coffee and Poster Session / Kosilo, kava in predstavitev plakatov | |
| Urban Vesel & Matija Marolt | Odstranjevanje mašil v slovenskem govoru | |
| Vuk Dinić, Taja Kuzman Pungeršek, Peter Rupnik, Ivan Porupski & Nikola Ljubešić | The Dialectal Gap: Model Recency Dictates Commonsense Reasoning Performance in South Slavic Varieties | |
| Peter Rupnik & Nikola Ljubešić | Beyond WER and CER: Multi-Reference Evaluation for Slovenian Speech Recognition Benchmarking | |
| Neli Čatar, Andrej Miščič & Luka Vranješ | LES: Slovene Text Embedding Benchmark (Lestvica embeddingov za slovenščino) | |
| Nikola Ljubešić & Peter Rupnik | Persistence and Turnover on the South Slavic Web: A Study of Duplicate Content in CLASSLA-Web Corpora | |
| Špela Vintar, Mojca Brglez & Jan Jona Javoršek | Building the first comprehensive language and cultural competence benchmark for Slovene | |
| Frane Malenica & Emilija Mustapić Malenica | Large Language Corpora and Language Processing – The Effects of Frequency and Association Strenght on Multiword Expressions in L1 and L2 |
|
| Senja Pollak, Mateja Jemec Tomazin, Eva Pori, Hanh Thi Hong Tran & Špela Arhar Holdt | Luščenje terminologije pravic socialnega varstva | |
| Iztok Kosem & Špela Arhar Holdt | Od predloga do slovarja: Uporabniški predlogi v Slovarju sopomenk sodobne slovenščine | |
| Eva Pori, Matej Klemen, Tanja Jerman & Mihaela Knez | Ontologija tematskih polj za slovenščino kot drugi in tuji jezik – ONTEM 1.0 | |
| Alja Nike Kastrin, Nada Lavrač, Andrej Kastrin & Boshko Koloski | Comparing Supervised and Large Language Model-Based Approaches to Biomedical Word Sense Disambiguation | |
| Kristina Hmeljak Sangawa, Katarina Polšak, Katja Predalič & Ana Razinger | Sodelovalni knjižnični katalog v azijskih jezikih | |
| 13:15–13:20 | Group photo / Skupinsko fotografiranje | |
| 13:20–14:20 | Section 5 / Sekcija 5: Preparing and Analysing Historical Data / Priprava in analiza zgodovinskih podatkov (in English and Slovene) | Section Chair / Vodja sekcije: |
| 13:20–13:40 | Petra Bago & Mateo Žagar | An Accountable Human-in-the-Loop Workflow Specification for 16th-Century Croatian |
| 13:40–14:00 | Vojko Gorjanc, Filip Dobranić, Uroš Šmajdek, Oliver Pejić, Tina Munda & Darja Fišer | Combining Graph Visualisation and Critical Discourse Analysis in the Study of Slovene Historical Newspapers |
| 14:00–14:20 | Diana Košir & Massimo Sbarbaro | Digitalizacija in računalniška analiza rokopisnega indeksa knjižnega fonda pri sv. Ani v Kopru |
| 14:20–14:30 | Coffee Break / Odmor za kavo | |
| 14:30–16:10 | Section 6 / Sekcija 6: New Resources, Lexical Data and Lexicography / Novi viri, leksikalni podatki in leksikografija (in Slovene) | Section Chair / Vodja sekcije: |
| 14:30–14:50 | Andrej Zgank, Gregor Donaj, Urh Kolaric, Usi Sereinig, Tatjana Koren-Zwitter, Sanja Boto, Sabina Zwitter-Grilc, Jasna Vidinic & Darinka Verdonik | Korpus Zila: Govorni vir za raziskave in razvoj avtomatskega razpoznavanja za ziljsko narečje |
| 14:50–15:10 | Matej Klemen, Mojca Stritar Kučuk, Mateja Eniko & Damjan Huber | SEJO KOST: Razvoj novega jezikovnega vira za slovenščino kot neprvi jezik |
| 15:10–15:30 | Nina Zver & Matija Ogrin | Prekmurske pridige od prepisa do slovarja |
| 15:30–15:50 | Polona Gantar, Iztok Kosem, Tjaša Arčon & Simon Krek | Generiranje slovarskih definicij s pomočjo velikih jezikovnih modelov |
| 15:50–16:10 | Matic Pavlič & Andrej Perdih | 17.164 slovenskih psevdobesed: Empirično normiranje in psiholingvistični opis |
| 16.10–16.30 | Student Award Announcement and Conference Closing / Razglasitev študentske nagrade in zaključek konference | |
| 16:30–18:00 | Občni zbor SDJT / SDJT Annual Meeting |