Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Hakki Yagiz Erdinc"'
Publikováno v:
2022 30th Signal Processing and Communications Applications Conference (SIU).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::247a8afa47f7644caa8ee932aa6d780b
https://doi.org/10.1109/siu55565.2022.9864860
https://doi.org/10.1109/siu55565.2022.9864860
Publikováno v:
2022 2nd International Conference on Computing and Machine Intelligence (ICMI).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f6c4cbd4a0ef802e634f9b76c86758d
https://doi.org/10.1109/icmi55296.2022.9873663
https://doi.org/10.1109/icmi55296.2022.9873663
Publikováno v:
2020 28th Signal Processing and Communications Applications Conference (SIU).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4d65a3a4fd8d79519b19bd39d87c820
https://doi.org/10.1109/siu49456.2020.9302353
https://doi.org/10.1109/siu49456.2020.9302353
Publikováno v:
INISTA
Neural text classifiers of agglutinative languages often suffer from large vocabulary sizes of training data and high out of vocabulary rates during the test time. The natural language processing community has developed and used numerous word segment
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89576be7151689c2a279f247aea990e1
https://doi.org/10.1109/inista49547.2020.9194661
https://doi.org/10.1109/inista49547.2020.9194661
Publikováno v:
INISTA
Adult content filtering is an essential part of digital media platforms. With the extensive usage of social media, it becomes harder to overcome this problem. Traditional methods consist of human supervision and standalone image processing techniques
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0bca98dde28f8cd757c1fa3788f4c727
https://doi.org/10.1109/inista49547.2020.9194646
https://doi.org/10.1109/inista49547.2020.9194646
Autor:
Hakki Yagiz Erdinc, Aysun Güran
Publikováno v:
SIU
In this study, the performance values of Word2Vec, Doc2Vec and FastText algorithms are compared on the text categorization problem based on a semi-supervised learning technique. The impact of some preprocessing techniques are also analyzed on a corpu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c82dfd63744f4eee8fad7fc01a975b22
https://hdl.handle.net/11376/3580
https://hdl.handle.net/11376/3580
Publikováno v:
Data Science – Analytics and Applications ISBN: 9783658274948
Matching news articles from multiple different sources with different narratives is a crucial step towards advanced processing of online news flow. Although, there are studies about finding duplicate or near-duplicate documents in several domains, no
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9de1c53f2bc0564859d1c6837e4091b5
https://doi.org/10.1007/978-3-658-27495-5_3
https://doi.org/10.1007/978-3-658-27495-5_3