Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Semantic-conditioned sentence generation on FrameNet Before Filtering 1.7 (test)
Loading...
0.979
FE Fid.
Human (FN 1.7)
0.693
0.76725
0.8415
0.91575
Jun 7, 2024
FE Fid.
PPL
Human Acceptability Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
FE Fid.
PPL
Human Acceptability Score
Human (FN 1.7)
2024.06
0.979
78.1
1
Pancholy et al.
2024.06
0.953
127.8
0.611
T5 | Frame + FE
Conditioning=Frame+FE-...
2024.06
0.882
136.8
0.644
T5 | FE
Conditioning=FE-Condit...
2024.06
0.862
127.6
0.711
GPT-4 | Frame + FE
Conditioning=Frame+FE-...
2024.06
0.853
117.2
0.733
GPT-4 | FE
Conditioning=FE-Condit...
2024.06
0.841
106.3
0.7
T5
Conditioning=None
2024.06
0.784
139.3
0.594
GPT-4
Conditioning=None
2024.06
0.704
114.9
0.528
Feedback
Search any
task
Search any
task