Project Details

semANT - Sémantický průzkumník textového kulturního dědictví

Project Period: 1. 3. 2023 - 31. 12. 2027

Project Type: grant

Code: DH23P03OVV060

Agency: Ministry of Culture Czech Republic

Program: NAKI III program na podporu aplikovaného výzkumu v oblasti národní a kulturní identity na léta 2023 až 2030

English title
semANT - Semantic Document Exploration
Type
grant
Keywords

digital library, topic identification, semantic document search, content exploration, content visualization

Abstract

The main goal of this project is therefore to improve the possibilities of searching in the full-text representation of digitized documents at the level of text meaning and the possibilities of natural navigation between thematically similar documents. We provide users with a full-text search extended by understanding the meaning of queries, the ability to search by parts of the text (such as paragraphs) with the ability to specify at the same time the topic that interests him in the text. The system will work with automatically identified topics, but will allow users to define their own topics based on examples from texts.

Team members
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT) , research leader
Beneš Karel, Ing. (DCGM FIT BUT)
Dočekal Martin, Ing. (DCGM FIT BUT)
Fajčík Martin, Ing., Ph.D. (DCGM FIT BUT)
Kavalová Radka, Mgr. (RCIT FIT BUT)
Kišš Martin, Ing. (DCGM FIT BUT)
Kohút Jan, Ing. (DCGM FIT BUT)
Lampa Petr, Ing. (OIP FIT BUT)
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT)
Publications

2024

  • KIŠŠ Martin and HRADIŠ Michal. Self-supervised Pre-training of Text Recognizers. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds) Document Analysis and Recognition - ICDAR 2024. Lecture Notes in Computer Science, vol. 14807. Atény: Springer Nature Switzerland AG, 2024, pp. 218-235. ISBN 978-3-031-70545-8. Detail

2023

  • KOHÚT Jan and HRADIŠ Michal. Finetuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition. In: Document Analysis and Recognition - ICDAR 2023. Lecture Notes in Computer Science, vol. 14190. San José: Springer Nature Switzerland AG, 2023, pp. 269-286. ISBN 978-3-031-41684-2. ISSN 0302-9743. Detail
Products

2023

  • TextBite - System for analysis of document structure, software, 2023
    Authors: Kostelník Martin, Beneš Karel, Hradiš Michal, Vaško Marek Detail
Back to top