SOTAVerified

Passage Re-Ranking

Passage re-ranking is the task of scoring and re-ranking a collection of retrieved documents based on an input query.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 32 papers

TitleStatusHype
Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage ExpansionCode1
Multi-Granularity Guided Fusion-in-DecoderCode1
Towards Robust Passage Re-Ranking Model by Mitigating Lexical Match Bias—0
A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints—0
A Study on Passage Re-ranking in Embedding based Unsupervised Semantic Search—0
Efficient Document Ranking with Learnable Late Interactions—0
Improving Passage Re-Ranking with Word N-Gram Aware Coattention Encoder—0
Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking—0
Investigating the Successes and Failures of BERT for Passage Re-Ranking—0
Learning-to-Rank with BERT in TF-Ranking—0
Show:102550
← PrevPage 2 of 4Next →
All datasetsMS MARCOTREC-PM

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HLATRMRR0.42—Unverified
2BERT + Doc2queryMRR0.37—Unverified
3BERT + Small TrainingMRR0.36—Unverified
4Duet v2MRR0.25—Unverified
#ModelMetricClaimedVerifiedStatus
1BERT + Doc2querymAP36.5—Unverified