Výzkum užitečný pro společnost.
Project Details
MASAPI - Multilingvální asistent pro hledání, analýzu a zpracování informací a podporu rozhodování
Project Period: 1. 1. 2021 - 30. 4. 2024
Project Type: grant
Code: FW03010656
Agency: Technology Agency of the Czech Republic
Program: 3. veřejná soutěž - Program průmyslového výzkumu a experimentálního vývoje TREND, PODPROGRAM 1 TECHNOLOGIČTÍ LÍDŘI
assistance tool, artificial intelligence, multilingual application
The goal of the project is to create a multilingual tool for decision support and preparation of high-quality informative texts. The assistant will process available information (local files, e-mails, indexed websites) in commonly used formats (HTML, TXT, PDF, DOCX, XLSX, ODT etc.) and supported languages, build a knowledge base in these, reply to user's queries using this base and look up support for results in indexed documents.
The tool will be able to summarize large amounts of text and automatedly obtain data from a website saving the user's time. It will contain user-accessible AI tools for solving particular practical problems, e.g. from sales and marketing area. This highly multilingual application will be sold in Europe, the USA and South America.
Fajčík Martin, Ing., Ph.D. (UPGM FIT VUT)
Vrška Luděk (CVT FIT VUT)
2023
- FAJČÍK Martin, MOTLÍČEK Petr and SMRŽ Pavel. Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction. In: Findings of the Association for Computational Linguistics: ACL 2023. ACL, vol. 2023. Toronto: Association for Computational Linguistics, 2023, pp. 10184-10205. ISBN 978-1-959429-62-3. Detail
2022
- DOČEKAL Martin and SMRŽ Pavel. Query-Based Keyphrase Extraction from Long Documents. In: The International FLAIRS Conference Proceedings. 2022, vol. 2022. Jensen Beach: LibraryPress@UF, 2022, pp. 1-4. ISSN 2334-0762. Detail
2023
- MASAPI - Question Answering, software, 2023
Authors: Dočekal Martin, Smrž Pavel Detail - Official Implementation of Fact-Checking System "Claim-Dissector", software, 2023
Authors: Fajčík Martin, Smrž Pavel, Motlíček Petr Detail
2022
- Query-Based Extractor of Keyphrases, software, 2022
Authors: Dočekal Martin, Smrž Pavel Detail