Multimodal Document Understanding through Visual Question Answering – Bc. Šárka Ščavnická
Bc. Šárka Ščavnická
Master's thesis
Multimodal Document Understanding through Visual Question Answering
Multimodal Document Understanding through Visual Question Answering
Abstract:
Služby na spracovania dokumentov sú čoraz populárnejšie vo viacerých odvetviach, čo vedie k rastúcemu počtu výskumov použitia umelej inteligencie pri spracovaní dokumentov, táto oblasť je známa ako Document Intelligence. Táto práca sa zameriava na zodpovedanie otázok, ktoré sa týkajú dokumentov a ich vizuálnej stránky, skrátene známe pod pojmom DVQA (document visual question answering). Ide o podoblasť …moreAbstract:
Applications of document processing become increasingly popular across multiple industries, resulting in a growing amount of research on the applications of artificial intelligence in document processing, known as Document Intelligence. This paper focuses on Document Visual Question Answering, shortly known as DVQA, a subtask of Document Intelligence that is gaining attention for its universality. …more
Language used: English
Date on which the thesis was submitted / produced: 15. 12. 2023
Identifier:
https://is.muni.cz/th/wotad/
Thesis defence
- Date of defence: 8. 2. 2024
- Supervisor: Mgr. Michal Štefánik
- Reader: Edoardo Signoroni
Citation record
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Artificial intelligence and data processing / Big data
Theses on a related topic
-
Think Twice Before You Answer: Mitigating Biases of Question Answering Models
Lukáš Mikula -
Czech Question Answer Selection using Recurrent Neural Networks
Radoslav Sabol -
Automatic question answering for flective languages
Marek Medveď -
Think Twice Before You Answer: Mitigating Biases of Question Answering Models
Lukáš Mikula -
Automatic question answering for flective languages
Marek Medveď -
Question Answering technologie v právní praxi
Tomáš Nosek -
Czech Question Answer Selection using Recurrent Neural Networks
Radoslav Sabol