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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 31–40 of 41 papers

TitleStatusHype
End-to-End Neural Ad-hoc Ranking with Kernel PoolingCode0
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval ModelsCode0
Neural Ranking Models with Weak SupervisionCode0
PACRR: A Position-Aware Neural IR Model for Relevance MatchingCode0
GoWvis: A Web Application for Graph-of-Words-based Text Visualization and Summarization—0
Toward a Deep Neural Approach for Knowledge-Based IR—0
Query Expansion with Locally-Trained Word Embeddings—0
Text Matching as Image RecognitionCode1
Cumulative Progress in Language Models for Information Retrieval—0
Are Semantically Coherent Topic Models Useful for Ad Hoc Information Retrieval?—0
Show:102550
← PrevPage 4 of 5Next →

Benchmark Results

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