SberQuAD -- Russian Reading Comprehension Dataset: Description and Analysis

20 Dec 2019  ·  Pavel Efimov, Andrey Chertok, Leonid Boytsov, Pavel Braslavski ·

SberQuAD -- a large scale analog of Stanford SQuAD in the Russian language - is a valuable resource that has not been properly presented to the scientific community. We fill this gap by providing a description, a thorough analysis, and baseline experimental results.

PDF Abstract

Code
Add Remove Mark official

No code implementations yet. Submit your code now

Datasets

Introduced in the Paper:

SberQuAD

Used in the Paper:

SQuAD Natural Questions MS MARCO

Results from the Paper
Edit

 Ranked #1 on Question Answering on SberQuAD

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering SberQuAD DeepPavlov RuBERT EM 66.30+-0.24 # 1
Compare
F1 84.60+-0.11 # 1
Compare
Question Answering SberQuAD DeepPavlov R-Net EM 60.62 # 3
Compare
F1 80.04 # 3
Compare
Question Answering SberQuAD DeepPavlov multilingual BERT EM 64.35+-0.39 # 2
Compare
F1 83.39+-0.08 # 2
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy