HyperAI超神経

プラットフォーム

Passage Retrieval On Entityquestions

評価指標

Recall@20

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
TOME-2	0.838	Mention Memory: incorporating textual knowledge into Transformers through entity mention attention
SPAR-PAQ	0.740	Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
BM25	0.720	Simple Entity-Centric Questions Challenge Dense Retrievers
Zero-NeR	0.671	Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?
Contriever	0.647	Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?
DPR-multi	0.567	Simple Entity-Centric Questions Challenge Dense Retrievers
DPR-NQ	0.497	Simple Entity-Centric Questions Challenge Dense Retrievers

0 of 7 row(s) selected.

Passage Retrieval On Entityquestions | SOTA | HyperAI超神経