Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Semantic-conditioned sentence generation on FrameNet After Filtering 1.7 (test)
Loading...
97
PPL
Human (FN 1.7)
95.04
108.27
121.5
134.73
Jun 7, 2024
PPL
Human Acceptability Score
Instance Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
PPL
Human Acceptability Score
Instance Count
Human (FN 1.7)
2024.06
97
1
975
GPT-4 | FE
Conditioning=FE-Condit...
2024.06
103.4
0.826
838
GPT-4 | Frame + FE
Conditioning=Frame+FE-...
2024.06
111.8
0.821
845
T5 | FE
Conditioning=FE-Condit...
2024.06
112.7
0.777
850
GPT-4
Conditioning=None
2024.06
114.2
0.723
724
T5
Conditioning=None
2024.06
117.5
0.713
789
T5 | Frame + FE
Conditioning=Frame+FE-...
2024.06
124.4
0.704
873
Pancholy et al.
2024.06
146
0.686
947
Feedback
Search any
task
Search any
task