Slot Filling on KILT: Zero Shot RE

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	single ngram	74.63	No	-	-	-
2	Wikipedia	73.96	No	-	-	-
3	KGI_1	72.55	No	-	-	-
4	MetaRAG	71.61	No	-	-	-
5	KGI_0 (reupload)	68.97	No	-	-	-
6	Multitask DPR + BART	57.95	No	-	-	-
7	DensePhrases	47.42	No	Learning Dense Representations of Phrases at Scale	2020-12-23	Code
8	10k	47.42	No	-	-	-
9	RAG	44.74	No	-	-	-
10	Sphere	36.55	No	-	-	-
11	Coop. Distil Bert	36.23	No	-	-	-
12	BART + DPR	30.43	No	-	-	-
13	bart-base+ssm	11.22	No	-	-	-
14	BART	9.14	No	-	-	-
15	T5-base	9.02	No	KILT: a Benchmark for Knowledge Intensive Langua...	2020-09-04	Code
16	BERT + DPR	6.93	No	-	-	-
17	multi-task small	3.38	No	-	-	-
18	GENRE	0.02	No	-	-	-
19	chriskuei	0	No	-	-	-
20	TABi	0	No	-	-	-
21	Multi-task DPR	0	No	-	-	-

#1single ngram
74.63
Accuracy
No paper
#2Wikipedia
73.96
Accuracy
No paper
#3KGI_1
72.55
Accuracy
No paper
#4MetaRAG
71.61
Accuracy
No paper
#5KGI_0 (reupload)
68.97
Accuracy
No paper
#6Multitask DPR + BART
57.95
Accuracy
No paper
#7DensePhrasesSOTA
47.42
Accuracy· 2020-12-23
Learning Dense Representations of Phrases at Scale Code
#810k
47.42
Accuracy
No paper
#9RAG
44.74
Accuracy
No paper
#10Sphere
36.55
Accuracy
No paper
#11Coop. Distil Bert
36.23
Accuracy
No paper
#12BART + DPR
30.43
Accuracy
No paper
#13bart-base+ssm
11.22
Accuracy
No paper
#14BART
9.14
Accuracy
No paper
#15T5-baseSOTA
9.02
Accuracy· 2020-09-04
KILT: a Benchmark for Knowledge Intensive Language Tasks Code
#16BERT + DPR
6.93
Accuracy
No paper
#17multi-task small
3.38
Accuracy
No paper
#18GENRE
0.02
Accuracy
No paper
#19chriskuei
0
Accuracy
No paper
#20TABi
0
Accuracy
No paper
#21Multi-task DPR
0
Accuracy
No paper