
Venue: Prof. Marin Drinov Hall in the BAS Administration Building (15 November Street No. 1, Sofia)
Time: October 24, 2025, from 09:00 to 15:30.
CLaDA-BG is a National Interdisciplinary Research E-Infrastructure for Bulgarian Language and Cultural Heritage Resources and Technologies integrated within European CLARIN and DARIAH infrastructures (https://clada-bg.eu/).
The event consists of three sessions:
- Session on technologies and resources of CLaDA-BG
- Demo session – presentation of software and services
- Session on resources – presentation of collections, e-books, artifacts
Software systems, services, and databases developed in the field of social sciences and humanities (SS&H) will be presented, as well as other related materials created in the context of CLaDA-BG and its partner initiatives.
The aim of the event is to present the achievements and development of CLaDA-BG, to encourage the exchange of experience between researchers, and to outline opportunities for cooperation within the national and European research system.
Program
09:00 Opening
Session on technologies and resources of CLaDA-BG
09:15 Presenting of CLaDA-BG (Kiril Simov, IICT-BAS)
09:30 Language resources and technologies, large language models for processing data in Bulgarian (Petya Osenova, IICT-BAS and Sofia University)
09:50 Knowledge base, services, and large language models for knowledge extraction (Kiril Simov, IICT-BAS)
10:10 3D technologies, models, and projects (Ivan Georgiev, IICT-BAS)
10:30 Coffee break
11:00 CultIS – software platform for intelligent digital management and presentation of large arrays of data and knowledge from the humanities and social sciences. Applications. (Desislava Paneva-Marinova, IMI-BAS)
11:20 From scriptorium to server: digital infrastructures for cultural heritage research (Tsvetan Vassilev and Kristian Simeonov, Sofia University)
11:40 Modern solutions for presenting cultural and historical heritage: the example of the manuscript and literary heritage of Neofit Bozveli (Yura Konstantinova, IBCT-BAS)
12:00 The web-based LABMETA system – parameters, functionalities (Zhaneta Andreeva, Shumen University)
12:20 Lunch
Demo session and Session on resources
14:00
Demonstration of software systems and services
Posters dedicated to resources: Language, history, culture
- Stefka Alexandrova. PoliteLab – web-based system for creating a multilingual online dictionary of speech etiquette (developed under the National Scientific Program “Development and Promotion of Bulgarian Studies Abroad”, inspired by CLaDA-BG).
- Ani Angelova. PhrasoLAB-BG – web-based platform for learning Bulgarian and German phraseological units
- Zhaneta Andreeva. LABMETA – web-based system for researching cognitive metaphors in Bulgarian political speeches
- Tsvetan Vassilev. The Cyril and Methodius tradition in CLaDA-BG: sources, manuscripts, artifacts.
- Valentin Vitanov. Stories behind the facades: Zahari Alkalay’s residential building
- Teodor Valchev and Nikolay Paev. Visualization of annotated documents with large language models
- Mario Filipov. Stories behind the facades: Dr. Kostov’s house
- Dimitar Minev and Ivan Krachanov. Digital library of the National Library of Bulgaria in Plovdiv
- Ivaylo Nachev. It grows, but does not age: semantic and 3D technologies for the history of the streets and buildings in Sofia.
- Desislava Paneva-Marinova. CultIS – software platform for intelligent digital management and presentation of large arrays of data and knowledge from the humanities and social sciences. Applications.
- Nikolay Petkov. Digital vision for ancient artifacts: Research on ceramic vessels for aromatic oil from ancient Thrace
- Nikolay Petkov. Three-dimensional virtual reconstruction of a late Hellenistic kerosene lamp from Voditsi, Northeastern Bulgaria
- Milen Petrov. Historical Chameleons
- Velka Popova, Dimitar Popov. Bulgarian corpus in the interactive platform CHILDES
- Velka Popova, Dimitar Popov. Lablass – web-based system for studying word associations
- Karina Simeonova. Stories Behind the Facades: Hotel Prentan
- Kiril Simov, Petya Osenova, Stefan Marinov, Nikolay Paev, Kristin Dimitrova, Tsvetelina Aleksandrova. Bulgarian Event Corpus: Models for Extracting Knowledge from Text
- Kiril Simov, Nikolay Paev, Petya Osenova. LLM-based Models for Transforming of Diachronic Bulgarian Spelling to Contemporary Bulgarian
15:30 Closing



