Other formats:
BibTeX
LaTeX
RIS
@inproceedings{2234001,
author = {Ščavnická, Šárka and Štefánik, Michal and Kadlčík, Marek and Geletka, Martin and Sojka, Petr},
address = {Brno},
booktitle = {Recent Advances in Slavonic Natural Language Processing (RASLAN 2022)},
edition = {Recent Advances in Slavonic},
keywords = {Question Answering; Visual Question Answering; Document Visual Question Answering},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Brno},
isbn = {978-80-263-1752-4},
pages = {181-188},
publisher = {Tribun EU},
title = {Towards General Document Understanding through Question Answering},
url = {https://nlp.fi.muni.cz/raslan/2022/paper17.pdf},
year = {2022}
}
TY - JOUR
ID - 2234001
AU - Ščavnická, Šárka - Štefánik, Michal - Kadlčík, Marek - Geletka, Martin - Sojka, Petr
PY - 2022
TI - Towards General Document Understanding through Question Answering
PB - Tribun EU
CY - Brno
SN - 9788026317524
KW - Question Answering
KW - Visual Question Answering
KW - Document Visual Question Answering
UR - https://nlp.fi.muni.cz/raslan/2022/paper17.pdf
N2 - Document Visual Question Answering is a relatively new extension of Visual Question Answering. The aim is to understand the documents and to be able to obtain information that corresponds to the question that was asked. This proposition aims to approach the problem of the lack of datasets and a model for Slavic languages. Therefore we would like to create a model and dataset for Document VQA suitable for the non-English language. This paper overviews the field of Question Answering and also describes the first Czech Document VQA dataset and model.
ER -
ŠČAVNICKÁ, Šárka, Michal ŠTEFÁNIK, Marek KADLČÍK, Martin GELETKA and Petr SOJKA. Towards General Document Understanding through Question Answering. In \textit{Recent Advances in Slavonic Natural Language Processing (RASLAN 2022)}. Recent Advances in Slavonic. Brno: Tribun EU, 2022, p.~181-188. ISBN~978-80-263-1752-4.
|
