Transformer-based Tagging
Transformer-Based Tagging is a part-of-speech tagging method that employs transformer architectures to model contextual dependencies in text through self-attention mechanisms, distinguishing itself from rule-based, statistical, or recurrent neural approaches by leveraging parallelized, context-aware representations for improved tag prediction accuracy.
39
Publications
1.6K
Citations
174
Authors
62
Institutions
Publications per year
2017–2026
39
Parents
39
Wietse de Vries, Andreas van Cranenburgh, Arianna Bisazza et al. · arXiv (Cornell University) · 2019 · 215 citations · Full text
GREEK-BERT: The Greeks visiting Sesame Street
John Koutsikakis, Ilias Chalkidis, Prodromos Malakasiotis et al. · 2020 · 84 citations · Full text
1–5 of 39
174
2
h-index
International Institute for Applied Systems Analysis, Austria
2 publications · 286 citations
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 174
62
University of Zurich
Zurich, Switzerland
2 h-index
4 publications
216 citations
University of California, Berkeley
Berkeley, United States
2 h-index
3 publications
287 citations

Shanghai Jiao Tong University
Shanghai, China
2 h-index
2 publications
84 citations
North Dakota State University
Fargo, United States
2 h-index
6 publications
192 citations
Stanford University
Stanford, United States
2 h-index
4 publications
353 citations
The University of Texas at Austin
Austin, United States
1 h-index
1 publications
13 citations
Hamad bin Khalifa University
Doha, Qatar
1 h-index
2 publications
30 citations

University of Birmingham
Birmingham, United Kingdom
1 h-index
1 publications
17 citations
1–8 of 62
Repository · 11 publications · 515 citations
10
h-index
Conference · 2 publications · 52 citations
2
h-index
1 publications · 19 citations
1
h-index
1 publications · 38 citations
1
h-index
1 publications · 15 citations
1
h-index
1–5