ELECTRA-Base + SSP

Reported on 2 benchmarks across 1 task · 1 paper

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

Natural Language Processing2 results

Question AnsweringonASNQ
MAP· 2022-05-20
0.697
best: 0.743 (DeBERTa-V3-Large + SSP)
Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection arXiv:2205.10455
Question AnsweringonASNQ
MRR· 2022-05-20
0.757
best: 0.8 (DeBERTa-V3-Large + SSP)
Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection arXiv:2205.10455