NPRF-DRMM

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

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

Natural Language Processing3 results

Ad-Hoc Information RetrievalonTREC Robust04
MAP· 2018-10-30
0.2904
best: 0.3876 (monoT5-3B (zero-shot))
SOTA
NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval arXiv:1810.12936
Ad-Hoc Information RetrievalonTREC Robust04
P@20· 2018-10-30
0.4064
best: 0.5165 (monoT5-3B (zero-shot))
SOTA
NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval arXiv:1810.12936
Ad-Hoc Information RetrievalonTREC Robust04
nDCG@20· 2018-10-30
0.4502
best: 0.6091 (monoT5-3B (zero-shot))
NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval arXiv:1810.12936