Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Tokenization on TWEEBANK V2 (test)
Loading...
98.64
F1 Score
Stanza
94.4384
95.5292
96.62
97.7108
Apr 23, 2018
Dec 6, 2018
Jul 22, 2019
Mar 6, 2020
Oct 19, 2020
Jun 4, 2021
Jan 18, 2022
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
Stanza
Training Data=TB2
2022.01
98.64
Stanza
Training Data=TB2+EWT
2022.01
98.59
spaCy
Training Data=TB2
2022.01
98.57
bi-LSTM tokenizer
Hidden units=64, RNN T...
2018.04
98.3
twpipe
Pipeline stage=Tokeniz...
2018.04
98.3
Twpipe
2022.01
98.3
UDPipe v1.2
Training=re-trained on...
2018.04
97.4
UDPipe v1.2
2022.01
97.4
Stanford CoreNLP
Type=rule-based
2018.04
97.3
Stanford CoreNLP tokenizer
Pipeline stage=Tokeniz...
2018.04
97.3
Stanford CoreNLP
2022.01
97.3
spaCy
Training Data=TB2+EWT
2022.01
95.57
Twokenizer
Type=rule-based, Versi...
2018.04
94.6
Twokenizer
2022.01
94.6
Feedback
Search any
task
Search any
task