Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
MWE Paraphrasing on English MWE SemEval (test)
Loading...
13.2
P@1
GPT-3
6.336
8.118
9.9
11.682
Jun 2, 2023
P@1
P@5
P@10
Updated 4d ago
Evaluation Results
Method
Method
Links
P@1
P@5
P@10
GPT-3
# param=175B
2023.06
13.2
-
-
T5-base
# param=220M, rerank=f...
2023.06
10.8
22
25.8
T5-base
# param=220M, rerank=true
2023.06
10.1
22.6
27.1
SpanBERT
# param=340M
2023.06
8.5
22
28.9
BERT-base
# param=110M
2023.06
8.2
18.4
24.3
BERT-large
# param=340M
2023.06
8.1
19.4
27.6
T5-large
# param=770M, rerank=f...
2023.06
8
22.5
28
T5-large
# param=770M, rerank=true
2023.06
7.2
25.6
33.3
ALBERT
# param=17M
2023.06
6.6
13.5
21.3
Feedback
Search any
task
Search any
task
