Presentations at scientific events
2026. Bulgarian Massive Multitask Language Understanding Benchmark.
15th Language Resources and Evaluation Conference (LREC 2026), Palma de Mallorca, 11–16 May 2026.
2026. IfGPT, a Large Dataset Representing Bulgarian, with the Bulgarian National Corpus as Its Core.
12th Workshop on Challenges in the Management of Large Corpora (CMLC-12) @ LREC 2026, Palma de Mallorca, 11 May 2026.
2026. Recent Developments of the Bulgarian National Corpus.
12th Workshop on Challenges in the Management of Large Corpora (CMLC-12) @ LREC 2026, Palma de Mallorca, 11 May 2026.
2025. Infrastructure for Fine-Tuning Pre-Trained Large Language Models (IfGPT).
International Forum on Advanced ICT Research and Innovation, 30 Sep – 1 Oct 2025.
2025. Fusion of Object-Centric and Linguistic Features for Domain-Adapted Multimodal Learning.
RANLP 2025, Varna, Bulgaria, 8–13 Sep 2025.
2025. Large Language Models for Lexical Resource Enhancement: Multiple Hypernymy Resolution in WordNet.
9th Student Research Workshop @ RANLP 2025, Varna, Bulgaria, 8–13 Sep 2025.
2025. IfGPT: A Dataset in Bulgarian for Large Language Models.
1st Workshop on Advancing NLP for Low-Resource Languages (LowResNLP) @ RANLP 2025, Varna, 13 Sep 2025.
Presentation of the results of the project “Infrastructure for Fine-Tuning Pre-trained Large Language Models”, 29/05/2026, Sofia
2026. Големият набор от езикови данни IfGPT: управление на метаданните и осигуряване на качеството на данните.
[The large dataset IfGPT: Metadata management and quality of the data]
2026. Инфраструктура за създаване на чатбот с големи езикови модели и контекстно разширяване на инструкциите.
[Infrastructure for developing a chatbot with LLMs and RAG]
2026. Набори от данни на български език за оценка на големи езикови модели.
[Benchmarks in Bulgarian for assessment of LLMs]
Media Coverage of the Project
Dimitar Hristov talks about computational linguistics and why he chose to become a PhD student in the Computational Linguistics Section
Prof. Svetla Koeva: It matters how the legislation on artificial intelligence will be drafted
The Bulgarian Telegraph Agency and the Institute for Bulgarian Language at the Bulgarian Academy of Sciences signed a partnership agreement
BTA and the Institute for Bulgarian Language at BAS signed a partnership agreement
It is natural for BTA to cooperate with BAS and the Institute for Bulgarian Language, because these are institutions that symbolise spiritual values, said Prof. Dr. Svetla Koeva
Our cooperation with BTA is very thematic and extensive, said the President of the Bulgarian Academy of Sciences, Corr. Member Evelina Slavcheva
We view AI positively — it is our responsibility how we will use it
The language models project provides expert data in Bulgarian for AI systems, said Prof. Svetla Koeva
Scientists and businesses can train AI on verified Bulgarian data
AI without million-euro budgets: BAS platform opens its doors to Bulgarian business
BAS platform opens its doors to Bulgarian business with ready-made AI models