Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Eronen, Juuso"'
Publikováno v:
Information Processing & Management 2023
The struggle of social media platforms to moderate content in a timely manner, encourages users to abuse such platforms to spread vulgar or abusive language, which, when performed repeatedly becomes cyberbullying a social problem taking place in virt
Externí odkaz:
http://arxiv.org/abs/2308.15745
This paper investigates the impact of data volume and the use of similar languages on transfer learning in a machine translation task. We find out that having more data generally leads to better performance, as it allows the model to learn more patte
Externí odkaz:
http://arxiv.org/abs/2306.00660
Publikováno v:
Information Processing & Management, Volume 60, Issue 3, 2023, 103250
We study the selection of transfer languages for different Natural Language Processing tasks, specifically sentiment analysis, named entity recognition and dependency parsing. In order to select an optimal transfer language, we propose to utilize dif
Externí odkaz:
http://arxiv.org/abs/2301.13720
Comparing Performance of Different Linguistically-Backed Word Embeddings for Cyberbullying Detection
Publikováno v:
Proceedings of the 2021 International Workshop on Modern Science and Technology, September 29, 2021
In most cases, word embeddings are learned only from raw tokens or in some cases, lemmas. This includes pre-trained language models like BERT. To investigate on the potential of capturing deeper relations between lexical items and structures and to f
Externí odkaz:
http://arxiv.org/abs/2206.01950
Publikováno v:
he 7th Workshop on Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA 2021) collocated with IJCAI 2021,August 21--26th, 2021, Montreal, Canada. CEUR Workshop Proceedings 2935, 5-14
In this research. we analyze the potential of Feature Density (HD) as a way to comparatively estimate machine learning (ML) classifier performance prior to training. The goal of the study is to aid in solving the problem of resource-intensive trainin
Externí odkaz:
http://arxiv.org/abs/2206.01949
Autor:
Eronen, Juuso, Ptaszynski, Michal, Masui, Fumito, Leliwa, Gniewosz, Wroczynski, Michal, Piech, Mateusz, Smywinski-Pohl, Aleksander
Publikováno v:
Proceedings of The 6th Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA 2020) IJCAI 2020 Workshop, Yokohama, Japan, January 2020
In this research, we study the change in the performance of machine learning (ML) classifiers when various linguistic preprocessing methods of a dataset were used, with the specific focus on linguistically-backed embeddings in Convolutional Neural Ne
Externí odkaz:
http://arxiv.org/abs/2206.01889
Autor:
Eronen, Juuso, Ptaszynski, Michal, Masui, Fumito, Arata, Masaki, Leliwa, Gniewosz, Wroczynski, Michal
Publikováno v:
Information Processing & Management, Volume 59, Issue 4, July 2022, paper ID: 102981
We study the selection of transfer languages for automatic abusive language detection. Instead of preparing a dataset for every language, we demonstrate the effectiveness of cross-lingual transfer learning for zero-shot abusive language detection. Th
Externí odkaz:
http://arxiv.org/abs/2206.00962
Publikováno v:
In Natural Language Processing Journal December 2024 9
Autor:
Eronen, Juuso, Ptaszynski, Michal, Masui, Fumito, Smywiński-Pohl, Aleksander, Leliwa, Gniewosz, Wroczynski, Michal
Publikováno v:
Information Processing and Management, Vol. 58, Issue 5, September 2021, paper ID: 102616
We study the effectiveness of Feature Density (FD) using different linguistically-backed feature preprocessing methods in order to estimate dataset complexity, which in turn is used to comparatively estimate the potential performance of machine learn
Externí odkaz:
http://arxiv.org/abs/2111.01689
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.