Sparse Attention

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Question AnsweringonQuasart-T
EM· 2019-04-23
52.1
best: 54 (Cluster-Former (#C=512))
SOTA
Generating Long Sequences with Sparse Transformers arXiv:1904.10509
Question AnsweringonNatural Questions (long)
F1· 2019-04-23
74.5
best: 79.6 (DensePhrases)
SOTA
Generating Long Sequences with Sparse Transformers arXiv:1904.10509
Question AnsweringonSearchQA
EM· 2019-04-23
64.7
best: 68 (Cluster-Former (#C=512))
SOTA
Generating Long Sequences with Sparse Transformers arXiv:1904.10509
Open-Domain Question AnsweringonSearchQA
EM· 2019-04-23
64.7
best: 68 (Cluster-Former (#C=512))
SOTA
Generating Long Sequences with Sparse Transformers arXiv:1904.10509