NLP Seminar videos
List of talks:
- 23.10.2025 Ian Lapkin: Automatic Sign Language Processing
- 2.10.2025 Petr Zelina: Czech Clinical Note Mining: Comparing LLMs
- 25.9.2025 Jan Brichta: Text Classification for Machine Translation Models
- 4.4.2025 Petr Zelina: Extracting clinical note elements from pathology reports
- 21.10.2024 Vojtěch Formánek: Jailbreaking Empathy
- 7.10.2024 Ondřej Valášek: Terminology Extraction Evaluation
- 25.4.2024 David Porteš: Driving LLMs using Prosody
- 11.4.2024 Tomáš Houfek: Medical Named Entity Recognition (and more)
- 30.11.2023 Adam Karásek: Authorship identification
- 4.4.2023 Michal Měchura: Issues and challenges when encoding dictionaries on computers
- 25.5. Michal Starý: Event Detection
- 18.5. Ondřej Sotolář: Building a Corpus for Personal Data Detection
- 11.5. Krištof Anetta: Electronic Health Records processing, Apache cTakes
- 4.5. Petr Zelina: ALBERT Training
- 27.4. Pavel Rychlý: Using Makefiles for NLP projects
- 16.4. Vítek Novotný: When FastText Pays Attention
- 13.4. Mikuláš Bankovič: Application of super-resolution on OCR of historical documents
- 13.4. Adam Hájek: výpočet GTP-2 na Metacentru
- 30.3. Hien Thi Ha: Block type classification from scanned invoices
- 23.3. Michal Štefánik: Unsupervised Estimation of Out-of-Domain Performance of Language Models
- 23.3. Marek Medveď: SQAD database update
- 16.3. Vítek Novotný: EDS-MEMBED: Multi-Sense Embeddings Based on Enhanced Distributional Semantic Structures via a Graph Walk over Word Senses
- 12.1. Ondřej Sotolář: Anonymizace dokumentů
- 8.12. Radoslav Sabol: Officebot
- 1.12. Adam Hájek: Automatic Text Summarization
- 27.10. Vít Novotný: When Tesseract does it alone
- 13.10. Vít Novotný, 2 talks
- 13.5. Hien Thi Ha: Information extraction from contracts
- 6.5. Michal Starý: Event Miner
- 22.4. Petr Zelina: Evaluating Czech ALBERT
- 22.4. Marie Stará: Automatic creation of explanations
- 15.4. Veronika Burgerová: Paraphrase Generation for Czech
- 8.4. Vít Novotný: Joint word embeddings and soft cosine measure at ARQMath
- 1.4. Renáta Pivodová: Zpracování nových gramatických fenoménů v logické analýze PJ
- 1.4. Michal Hala: Implementace efektivní sémantické sítě pro reprezentací znalostí
23.10.2025 Ian Lapkin: Automatic Sign Language Processing
2.10.2025 Petr Zelina: Czech Clinical Note Mining: Comparing LLMs
25.9.2025 Jan Brichta: Text Classification for Machine Translation Models
4.4.2025 Petr Zelina: Extracting clinical note elements from pathology reports
21.10.2024 Vojtěch Formánek: Jailbreaking Empathy
7.10.2024 Ondřej Valášek: Terminology Extraction Evaluation
25.4.2024 David Porteš: Driving LLMs using Prosody
11.4.2024 Tomáš Houfek: Medical Named Entity Recognition (and more)
30.11.2023 Adam Karásek: Authorship identification
4.4.2023 Michal Měchura: Issues and challenges when encoding dictionaries on computers
25.5. Michal Starý: Event Detection
18.5. Ondřej Sotolář: Building a Corpus for Personal Data Detection
11.5. Krištof Anetta: Electronic Health Records processing, Apache cTakes
4.5. Petr Zelina: ALBERT Training
27.4. Pavel Rychlý: Using Makefiles for NLP projects
16.4. Vítek Novotný: When FastText Pays Attention
13.4. Mikuláš Bankovič: Application of super-resolution on OCR of historical documents
13.4. Adam Hájek: výpočet GTP-2 na Metacentru
30.3. Hien Thi Ha: Block type classification from scanned invoices
23.3. Michal Štefánik: Unsupervised Estimation of Out-of-Domain Performance of Language Models
23.3. Marek Medveď: SQAD database update
16.3. Vítek Novotný: EDS-MEMBED: Multi-Sense Embeddings Based on Enhanced Distributional Semantic Structures via a Graph Walk over Word Senses
12.1. Ondřej Sotolář: Anonymizace dokumentů
8.12. Radoslav Sabol: Officebot
1.12. Adam Hájek: Automatic Text Summarization
27.10. Vít Novotný: When Tesseract does it alone
13.10. Vít Novotný, 2 talks
MIR@MU at ARQMath 2020, link to citation in chat
Enhancing word embeddings: Positionality, subword sizes, and hyphenation
13.5. Hien Thi Ha: Information extraction from contracts
Presentation
Questions in the discussion
6.5. Michal Starý: Event Miner
Presentation
Questions in the discussion
22.4. Petr Zelina: Evaluating Czech ALBERT
Presentation
Questions in the discussion
22.4. Marie Stará: Automatic creation of explanations
Presentation
Questions in the discussion
15.4. Veronika Burgerová: Paraphrase Generation for Czech
Presentation
Questions in the discussion
8.4. Vít Novotný: Joint word embeddings and soft cosine measure at ARQMath
Presentation
Questions in the discussion
1.4. Renáta Pivodová: Zpracování nových gramatických fenoménů v logické analýze PJ
Presentation
Questions in the discussion
1.4. Michal Hala: Implementace efektivní sémantické sítě pro reprezentací znalostí
Presentation
Questions in the discussion