BERTserini

Reported on 2 benchmarks across 2 tasks · 2 papers · 2 SOTA

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

Natural Language Processing4 results

Open-Domain Question AnsweringonSQuAD1.1 dev
EM· 2019-04-14
50.2
best: 59.3 (SPARTA)
SOTA
Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering arXiv:1904.06652
Open-Domain Question AnsweringonSQuAD1.1 dev
EM· 2019-02-05
38.6
best: 59.3 (SPARTA)
SOTA
End-to-End Open-Domain Question Answering with BERTserini arXiv:1902.01718
Question AnsweringonSQuAD1.1 dev
EM· 2019-04-14
50.2
best: 90.06 (T5-11B)
Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering arXiv:1904.06652
Question AnsweringonSQuAD1.1 dev
EM· 2019-02-05
38.6
best: 90.06 (T5-11B)
End-to-End Open-Domain Question Answering with BERTserini arXiv:1902.01718