Project Details

Pokročilé sémantické obohacování vícejazyčných kolekcí literárních textů

Project Period: 1. 6. 2018 - 31. 10. 2021

Project Type: grant

Code: LTC18054

Agency: Ministry of Education, Youth and Sports Czech Republic

Program: INTER-EXCELLENCE - Podprogram INTER-COST

English title
Distant Reading for European Literary History
Type
grant
Keywords

Semantics; Metadata Extraction

Abstract

The project will contribute to the activities of COST Action CA 16204 - Distant-Reading - in the areas related to semantic enrichment of large collections of literary texts in various languages. We will research and develop advanced methods of metadata extraction and content annotation, making explicit a wide range of semantic structures in texts, explore novel techniques to adapt existing resources and tools to new languages, domains, and contexts, and study new ways to efficiently manage collected resources and to check their quality and consistency.

Team members
Smrž Pavel, doc. RNDr., Ph.D. (UPGM FIT VUT) , research leader
Publications

2021

  • FAJČÍK Martin, DOČEKAL Martin, ONDŘEJ Karel and SMRŽ Pavel et al. R2-D2: A Modular Baseline for Open-Domain Question Answering. In: Findings of the Association for Computational Linguistics: EMNLP 2021. Findings of the Association for Computational Linguistics. Punta Cana: Association for Computational Linguistics, 2021, pp. 854-870. ISBN 978-1-955917-10-0. Detail
  • FAJČÍK Martin, JON Josef and SMRŽ Pavel. Rethinking the Objectives of Extractive Question Answering. In: Proceedings of the 3rd Workshop on Machine Reading for Question Answering. Proceedings of the 3rd Workshop on Machine Reading for Question Answering. Punta Cana: Association for Computational Linguistics, 2021, pp. 14-27. ISBN 978-1-954085-95-4. Detail

2020

  • JON Josef, FAJČÍK Martin, DOČEKAL Martin and SMRŽ Pavel. BUT-FIT at SemEval-2020 Task 4: Multilingual commonsense. In: Proceedings of the Fourteenth Workshop on Semantic Evaluation. Barcelona: Association for Computational Linguistics, 2020, pp. 374-390. ISBN 978-1-952148-31-6. Detail
  • DOČEKAL Martin, FAJČÍK Martin, JON Josef and SMRŽ Pavel. JokeMeter at SemEval-2020 Task 7: Convolutional Humor. In: Proceedings of the Fourteenth Workshop on Semantic Evaluation. 2020. Barcelona (online): Association for Computational Linguistics, 2020, pp. 843-851. ISBN 978-1-952148-31-6. Detail

2019

  • FAJČÍK Martin, BURGET Lukáš and SMRŽ Pavel. BUT-FIT at SemEval-2019 Task 7: Determining the Rumour Stance with Pre-Trained Deep Bidirectional Transformers. In: Proceedings of the 13th International Workshop on Semantic Evaluation. Minneapolis, Minnesota: Association for Computational Linguistics, 2019, pp. 1097-1104. ISBN 978-1-950737-06-2. Detail
Products

2021

  • R2-D2: System for Open-Domain Question Answering, software, 2021
    Authors: Fajčík Martin, Dočekal Martin, Ondřej Karel, Smrž Pavel Detail
  • Rethinking the Objectives of Extractive Question Answering, software, 2021
    Authors: Fajčík Martin, Jon Josef, Smrž Pavel Detail

2019

  • Official implementation of BUT-FIT's solution from Rumoureval2019 competition, software, 2019
    Authors: Fajčík Martin, Burget Lukáš, Smrž Pavel Detail
Back to top