Table 1: 

Development set results on ms marco-Passage (MS-Passage), ms marco-Document (MS-Doc) showing MRR@10.

MS-PassageMS-Doc
ModelMRRMRR
Retrieval BM25 0.167 0.249 
 BM25-E 0.184 0.209 
 Doc2Query 0.215 - 
 docT5query 0.278 - 
 DeepCT 0.243 - 
 hdct - 0.300 
 de-bert 0.302 0.288 
 me-bert 0.334 0.333 
 de-hybrid 0.304 0.313 
 de-hybrid-e 0.309 0.315 
 me-hybrid 0.338 0.346 
 me-hybrid-e 0.343 0.339 
 
Reranking Multi-Stage 0.390 - 
 idst 0.408 - 
 Leaderboard 0.439 - 
 de-bert 0.391 0.339 
 me-bert 0.395 0.353 
 me-hybrid 0.394 0.353 
MS-PassageMS-Doc
ModelMRRMRR
Retrieval BM25 0.167 0.249 
 BM25-E 0.184 0.209 
 Doc2Query 0.215 - 
 docT5query 0.278 - 
 DeepCT 0.243 - 
 hdct - 0.300 
 de-bert 0.302 0.288 
 me-bert 0.334 0.333 
 de-hybrid 0.304 0.313 
 de-hybrid-e 0.309 0.315 
 me-hybrid 0.338 0.346 
 me-hybrid-e 0.343 0.339 
 
Reranking Multi-Stage 0.390 - 
 idst 0.408 - 
 Leaderboard 0.439 - 
 de-bert 0.391 0.339 
 me-bert 0.395 0.353 
 me-hybrid 0.394 0.353 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept