SOTAVerified

Ad-Hoc Information Retrieval

Ad-hoc information retrieval refers to the task of returning information resources related to a user query formulated in natural language.

Papers

Showing 2130 of 41 papers

TitleStatusHype
Neural Ranking Models with Weak SupervisionCode0
NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information RetrievalCode0
PACRR: A Position-Aware Neural IR Model for Relevance MatchingCode0
Simple Applications of BERT for Ad Hoc Document RetrievalCode0
Teaching a New Dog Old Tricks: Resurrecting Multilingual Retrieval Using Zero-shot LearningCode0
Topical Coherence in LDA-based Models through Induced SegmentationCode0
CEDR: Contextualized Embeddings for Document RankingCode0
Neural document expansion for ad-hoc information retrieval0
DE-PACRR: Exploring Layers Inside the PACRR Model0
A data-driven strategy to combine word embeddings in information retrieval0
Show:102550
← PrevPage 3 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1monoT5-3B (zero-shot)nDCG@200.61Unverified
2PARADE(ELECTRA)nDCG@200.54Unverified
3CEDR-KNRMnDCG@200.54Unverified
4PARADE(BERT)nDCG@200.53Unverified
5BERT-MaxPnDCG@200.47Unverified
6BERT-SumPnDCG@200.47Unverified
7POSIT-DRMM-MVnDCG@200.46Unverified
8Vanilla BERTnDCG@200.45Unverified
9NPRF-DRMMnDCG@200.45Unverified
10PACRRnDCG@200.45Unverified