Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Matúš Pikuliak"'
Autor:
Jana Papcunová, Marcel Martončik, Denisa Fedáková, Michal Kentoš, Miroslava Bozogáňová, Ivan Srba, Robert Moro, Matúš Pikuliak, Marián Šimko, Matúš Adamkovič
Publikováno v:
Complex & Intelligent Systems, Vol 9, Iss 3, Pp 2827-2842 (2021)
Abstract Hate speech should be tackled and prosecuted based on how it is operationalized. However, the existing theoretical definitions of hate speech are not sufficiently fleshed out or easily operable. To overcome this inadequacy, and with the help
Externí odkaz:
https://doaj.org/article/c546bec3c1434be8b79835c8f51b77dc
Autor:
Matúš Pikuliak, Michal Kentoš, Denisa Fedáková, Matus Adamkovic, Robert Moro, Marcel Martončik, Marián Šimko, Miroslava Bozogáňová, Ivan Srba, Jana Papcunová
Publikováno v:
Complex & Intelligent Systems.
Hate speech should be tackled and prosecuted based on how it is operationalized. However, the existing theoretical definitions of hate speech are not sufficiently fleshed out or easily operable. To overcome this inadequacy, and with the help of inter
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8098148738508732cef6cfe59d01565f
https://doi.org/10.1007/s40747-021-00561-0
https://doi.org/10.1007/s40747-021-00561-0
Autor:
Matúš Pikuliak, Marián Šimko
Publikováno v:
Statistical Language and Speech Processing ISBN: 9783030594299
SLSP
SLSP
Many languages still lack the annotated training data needed for supervised learning. This issue is often addressed by using auxiliary supervision and the so called transfer learning. In this work we focus on the problem of combining two types of aux
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d8ea012b18f9593c690224538465256
https://doi.org/10.1007/978-3-030-59430-5_8
https://doi.org/10.1007/978-3-030-59430-5_8
Autor:
Marián Šimko, Matúš Pikuliak
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030583224
TDS
TDS
In this work we combine cross-lingual and cross-task supervision for zero-shot learning. Our main contribution is that we discovered that coupling models, i.e. models that share neither a task nor a language with the zero-shot target model, can impro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c1da0be025c13d9d9230f59bc2c036a
https://doi.org/10.1007/978-3-030-58323-1_17
https://doi.org/10.1007/978-3-030-58323-1_17
Publikováno v:
SOFSEM 2019: Theory and Practice of Computer Science ISBN: 9783030108007
SOFSEM
SOFSEM
Machine learning is an increasingly important approach to Natural Language Processing. Most languages however do not possess enough data to fully utilize it. When dealing with such languages it is important to use as much auxiliary data as possible.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e9f39c8a8dcdc1f5411878ab0e2ddcc
https://doi.org/10.1007/978-3-030-10801-4_34
https://doi.org/10.1007/978-3-030-10801-4_34
Autor:
Matúš Pikuliak, Michal Bojkovský
Publikováno v:
SemEval@NAACL-HLT
We present a number of models used for hate speech detection for Semeval 2019 Task-5: Hateval. We evaluate the viability of multilingual learning for this task. We also experiment with adversarial learning as a means of creating a multilingual model.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a186e3e34fb4abc34b7e6bbfdce53f14
https://doi.org/10.18653/v1/s19-2082
https://doi.org/10.18653/v1/s19-2082
Publikováno v:
Expert Systems with Applications. 165:113765
Many intelligent systems in business, government or academy process natural language as an input during inference or they might even communicate with users in natural language. The natural language processing is currently often done with machine lear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::971c620b4ccfffc14cfd081e754320b4
https://doi.org/10.1016/j.eswa.2020.113765
https://doi.org/10.1016/j.eswa.2020.113765
Publikováno v:
ALW
Growing amount of comments make online discussions difficult to moderate by human moderators only. Antisocial behavior is a common occurrence that often discourages other users from participating in discussion. We propose a neural network based metho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f32859e8637bf2b315b02e852ec280f
http://arxiv.org/abs/1809.06906
http://arxiv.org/abs/1809.06906
Autor:
Peter Gaspar, Michal Hucko, Cesare Pautasso, Matúš Pikuliak, Vasileios Triglianos, Mária Bieliková
Publikováno v:
2018 World Symposium on Digital Intelligence for Systems and Machines (DISA).
We aim to improve the communication process of a teacher with students during lectures using question answering. Our work is focused on the analysis of students' answers to support the teacher in his lecturing. We work with students' answers to open
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bdeba61f15320eca255583898cef5f7f
https://doi.org/10.1109/disa.2018.8490610
https://doi.org/10.1109/disa.2018.8490610
Autor:
Matúš Pikuliak
Publikováno v:
Scopus-Elsevier
Cross-lingual Learning can help to bring state-of-the-art deep learning solutions to smaller languages. These languages in general lack resource for training advanced neural networks. With transfer of knowledge across languages we can improve the res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6bfc1f8c0b107ca2c2680eece0966471
http://www.scopus.com/inward/record.url?eid=2-s2.0-85060474548&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85060474548&partnerID=MN8TOARS