Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Conversational Question Answering on CoQA (dev)
Loading...
0.849
Overall F1
UNILM
0.25204
0.40702
0.562
0.71698
Sep 27, 2018
Dec 17, 2018
Mar 8, 2019
May 28, 2019
Aug 17, 2019
Nov 6, 2019
Jan 26, 2020
Overall F1
Updated 3d ago
Evaluation Results
Method
Method
Links
Overall F1
UNILM
Mode=fine-tuned, Epoch...
2019.05
0.849
ERNIE-GENLARGE
beam size=3
2020.01
0.845
BERT_LARGE
Model type=cased, Mode...
2019.05
0.827
UNILMLARGE
2020.01
0.825
UNILM
fine-tuning epochs=10,...
2019.05
0.825
BiDAF++
Context window=3-ctx
2018.09
0.692
DrQA+ELMo
Architecture=LSTM-base...
2019.05
0.672
DrQA + PGNet
Type=Abstractive
2018.09
0.662
BiDAF++
Context window=0-ctx
2018.09
0.634
DrQA
Type=Extractive
2018.09
0.547
PGNet
2020.01
0.454
PGNet
architecture=Seq2Seq w...
2019.05
0.454
Seq2Seq
2020.01
0.275
Seq2Seq
architecture=sequence-...
2019.05
0.275
Feedback
Search any
task
Search any
task