| | 4 | |
| | 5 | |
| | 6 | === Seminar programme in the spring semester 2023 === #seminar_spring |
| | 7 | |
| | 8 | || '''date''' || '''programme''' || |
| | 9 | {{{#!th rowspan=1 |
| | 10 | '''14.2.''' |
| | 11 | }}} |
| | 12 | || seminar programme for this semester || |
| | 13 | {{{#!th rowspan=1 |
| | 14 | '''21.2.''' |
| | 15 | }}} |
| | 16 | || Pavel Rychlý: Data Processing || |
| | 17 | {{{#!th rowspan=2 |
| | 18 | '''28.2.''' |
| | 19 | }}} |
| | 20 | || Mauro Le Donne: Tokenisation of Italian Pre-trained Models || |
| | 21 | || Vítek Suchomel: Text processing in Linux – [https://drive.google.com/file/d/1q3jZriJqznKB3ejePuIuyBC1-enqMgOn/view hands on example] || |
| | 22 | {{{#!th rowspan=1 |
| | 23 | '''7.3.''' |
| | 24 | }}} |
| | 25 | || David Porteš: Discussion about Research Tools || |
| | 26 | {{{#!th rowspan=2 |
| | 27 | '''14.3.''' |
| | 28 | }}} |
| | 29 | || Katarína Hudcovicová: Propaganda detection || |
| | 30 | || Ondřej Sotolář: Explainability Tools – [https://docs.google.com/presentation/d/1ldO_4evdns7rJClSvquBgXfPuiu5ngYGl3q6WDatXs4/edit?usp=sharing link to presentation] || |
| | 31 | {{{#!th rowspan=1 |
| | 32 | '''21.3.''' |
| | 33 | }}} |
| | 34 | || ~~Hien Thi Ha: Information extraction from scanned documents~~ || |
| | 35 | {{{#!th rowspan=1 |
| | 36 | '''28.3.''' |
| | 37 | }}} |
| | 38 | || Edoardo Signoroni: Overview of Low-Resource Machine Translation || |
| | 39 | {{{#!th rowspan=1 |
| | 40 | '''4.4.''' |
| | 41 | }}} |
| | 42 | || Michal Měchura: [https://nlp.fi.muni.cz/trac/research/raw-attachment/wiki/en/NLPSeminar/mechura_pres.pdf Issues and challenges when encoding dictionaries on computers] || |
| | 43 | {{{#!th rowspan=2 |
| | 44 | '''11.4.''' |
| | 45 | }}} |
| | 46 | || Marek Medveď: Full AQA pipeline || |
| | 47 | || Krištof Anetta: Medical text content understanding || |
| | 48 | {{{#!th rowspan=1 |
| | 49 | '''18.4.''' |
| | 50 | }}} |
| | 51 | || Hien Thi Ha: Information extraction from scanned documents || |
| | 52 | {{{#!th rowspan=3 |
| | 53 | '''25.4.''' |
| | 54 | }}} |
| | 55 | || Ondřej Metelka: Automatic morphological paradigm construction || |
| | 56 | || Radoslav Sabol: [https://nlp.fi.muni.cz/trac/research/raw-attachment/wiki/en/NLPSeminar/nlp_seminar_spring_2023.pdf Optimizing the Inference of Neural Transformer Models] || |
| | 57 | || ~~Veronika Andrlová: Training a Czech Discussion Robot~~ || |
| | 58 | {{{#!th rowspan=2 |
| | 59 | '''2.5.''' |
| | 60 | }}} |
| | 61 | || Tomáš Houfek: Czech Medical Language Model and Document Classification || |
| | 62 | || Petr Zelina: Medical Data Processing || |
| | 63 | {{{#!th rowspan=2 |
| | 64 | '''9.5.''' |
| | 65 | }}} |
| | 66 | || Michaela Denisová: Cross-lingual embedding models || |
| | 67 | || Ondřej Sotolář: Conference report: AISTATS, EACL || |
| | 68 | |
| | 69 | |
| | 70 | |
| | 71 | |
| | 72 | |
