Current Students
- Klára Tauchmanová - Named entity recognition in historical texts (MSc)
- Igbal Huseynov - Topical segmentation of spoken narratives (MSc)
- Vojtěch Lanz - Information extraction from clinical documents (PhD)
- Christopher Brückner - Information extraction from historical documents (PhD)
- Jiří Mayer - Optical music recognition (PhD)
- Michal Auersperger - Neural representations (PhD)
Former Students
PhD
- Mateusz Krubiński - Multimodal summarization (2024).
- Shadi Saleh - Cross-lingual information retrieval in the medical domain (2020).
- Jindřich Libovický - Multimodality in machine translation (2019).
- Jan Hajič - Optical Recognition of handwritten music notation (2019).
- Aliya Nugumanova - Information retrieval with domain knowledge (2015, external, co-supervised).
- Petra Galuščáková - Information retrieval and navigation in audio-visual archives (2018).
MSc
- Nair Amrita Harikrishnan - Unsupervised open information extraction with large language models (2024, co-supervised)
- Karunakaran Goutham Venkatesh - Automatic relation extraction from clinical documents (2024, co-supervised)
- Jiří Mayer - Semi-supervised learning in optical music recognition (2022)
- David Vondrák - Recognition and classification of textbooks by deep learning (2022)
- Shadasha Williams - Named entity recognition in the biomedical domain (2021)
- Felipe Nascimento Vianna - Expert classification and retrieval (2020)
- Eric Lief - Deep contextualized word embeddings from character language models for neural sequence labeling (2019)
- Hoa Vu Trong - Grounding natural language inference on images (2018)
- Jonathan Oberländer - Splitting word compounds (2017)
- Karolína Burešová - Text simplification in Czech (2017)
- Michal Auersperger - English grammar checker and corrector: the determiners (2017)
- Ilana Rampula - Semantic relation extraction from unstructured data in the business domain (2016)
- Nguyen Tien Dat - Towards concept visualization through image generation (2016)
- Feraena Bibyna - Query expansion for medical information retrieval (2015)
- Sara Francisca Van de Moosdijk - Mining texts at the discourse level (2014, co-supervised)
- Jan Hajič - Matching images to texts (2014)
- Ondřej Odcházel - Automatic suggestion of illustrative images (2014)
- Duong Thanh Long - Universal POS tagger (2013, co-supervised)
- Jan Popelka - Automatic dictionary acquisition from parallel corpora (2011)
- Petra Galuščáková - Evaluation methods of systems for unsegmented speech retrieval (2011)
- Martin Kirschner - Automatic construction of semantic networks (2011)
- Sergio Raul Duarte Torres - Entity retrieval on Wikipedia in the scope of the gikiCLEF track (2010, co-supervised)
- Jana Straková - Syntax in methods for information retrieval (2009)
- Pavel Češka - Unsegmented speech retrieval (2008)
Bc
- Filip Danielsson - Towards a dataset for estimation of keyboard fingerings (2024, external)
- Jonáš Havelka - Music symbol genaration via neural networks (2023)
- Jiří Mayer - Optical music recognition using deep neural networks (2020}
- Radoslav Klíč - Document keyword extraction (2009)
- Česlav Przywara - Methods of multiword expression extraction from text (2008)
- Martin Majliš - Text sumarization (2008)
- Jan Sochna - Application for manual word alignment (2008)
- Michal Marek - Automatic HTML document cleaning (2007)
- Antonín Wimberský - Graph-based dependency parsing (2007)
- Lenka Smejkalová - Document similarity visualization (2007)
- Daniel Benčík - Near duplicate detection in large document collections (2007)
- Jana Kravalová - Automatic word alignment (2007)
- Daniel Lessner - Webcrawler (2006)
- Pavel Češka - Text segmentation (2006)