haritzpuerto commited on
Commit
125d0a5
1 Parent(s): f6be7d7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -18,8 +18,21 @@ This is the MADE encoder model created by Friedman et al. (2021). This encoder s
18
  - https://huggingface.co/UKP-SQuARE/MADE_NewsQA_Adapter
19
  - https://huggingface.co/UKP-SQuARE/MADE_NaturalQuestions_Adapter
20
 
 
21
 
 
 
 
 
 
 
 
22
 
23
 
 
 
 
 
 
24
  Citation:
25
  Single-dataset Experts for Multi-dataset Question Answering (Friedman et al., EMNLP 2021)
 
18
  - https://huggingface.co/UKP-SQuARE/MADE_NewsQA_Adapter
19
  - https://huggingface.co/UKP-SQuARE/MADE_NaturalQuestions_Adapter
20
 
21
+ Friedman et al. (2021) reported the following results:
22
 
23
+ - SQuAD v1.1: 92.4
24
+ - HotoptQA: 81.5
25
+ - TriviaQA: 80.5
26
+ - NewsQA: 72.1
27
+ - SearchQA: 85.8
28
+ - NaturalQuestions: 80.9
29
+ - Avg: 82.2
30
 
31
 
32
+ The UKP-SQuARE team created this model repository to simplify the deployment of this model on the UKP-SQuARE platform. The GitHub repository of the original authors is https://github.com/princeton-nlp/MADE
33
+
34
+
35
+ Please refer to the original publication for more information.
36
+
37
  Citation:
38
  Single-dataset Experts for Multi-dataset Question Answering (Friedman et al., EMNLP 2021)