Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1729476,
author = {Medveď, Marek and Sabol, Radoslav and Horák, Aleš},
address = {Brno},
booktitle = {Proceedings of the Fourteenth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2020},
editor = {Aleš Horák},
keywords = {question answering; dataset management; machine learning; optimization},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Brno},
isbn = {978-80-263-1600-8},
pages = {23-34},
publisher = {Tribun EU},
title = {Efficient Management and Optimization of Very Large Machine Learning Dataset for Question Answering},
url = {https://nlp.fi.muni.cz/raslan/raslan20.pdf#page=21},
year = {2020}
}
TY - JOUR
ID - 1729476
AU - Medveď, Marek - Sabol, Radoslav - Horák, Aleš
PY - 2020
TI - Efficient Management and Optimization of Very Large Machine Learning Dataset for Question Answering
PB - Tribun EU
CY - Brno
SN - 9788026316008
KW - question answering
KW - dataset management
KW - machine learning
KW - optimization
UR - https://nlp.fi.muni.cz/raslan/raslan20.pdf#page=21
N2 - Question answering strategies lean almost exclusively on deep neural network computations nowadays. Managing a large set of input data (questions, answers, full documents, metadata) in several forms suitable as the first layer of a selected network architecture can be a non-trivial task. In this paper, we present the details and evaluation of preparing a rich dataset of more than 13 thousand question-answer pairs with more than 6,500 full documents. We show, how a Python-optimized database in a network environment was utilized to offer fast responses based on the 26 GiB database of input data. A global hyperparameter optimization process with controlled running of thousands of evaluation experiments to reach a near-optimum setup of the learning process is also explicated.
ER -
MEDVEĎ, Marek, Radoslav SABOL and Aleš HORÁK. Efficient Management and Optimization of Very Large Machine Learning Dataset for Question Answering. In Aleš Horák. \textit{Proceedings of the Fourteenth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2020}. Brno: Tribun EU, 2020, p.~23-34. ISBN~978-80-263-1600-8.
|
