SOTAVerified

Passage Retrieval

Passage retrieval is a specialized type of IR application that retrieves relevant passages (or pieces of text) rather than an entire ranked set of documents.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 268 papers

TitleStatusHype
Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question AnsweringCode1
DAPR: A Benchmark on Document-Aware Passage RetrievalCode1
Query Performance Prediction: From Ad-hoc to Conversational SearchCode1
T2Ranking: A large-scale Chinese Benchmark for Passage RankingCode1
Do the Findings of Document and Passage Retrieval Generalize to the Retrieval of Responses for Dialogues?Code1
Query-as-context Pre-training for Dense Passage RetrievalCode1
Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single TransformerCode1
Cross-document Event Coreference Search: Task, Dataset and ModelingCode1
LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale RetrievalCode1
ConTextual Masked Auto-Encoder for Dense Passage RetrievalCode1
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage RetrievalCode1
Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query GenerationCode1
ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering SystemCode1
Optimizing Test-Time Query Representations for Dense RetrievalCode1
Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative TrainingCode1
Curriculum Learning for Dense Retrieval DistillationCode1
Improving Passage Retrieval with Zero-Shot Question GenerationCode1
CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with TyposCode1
Clickbait Spoiling via Question Answering and Passage RetrievalCode1
Augmenting Document Representations for Dense Retrieval with Interpolation and PerturbationCode1
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question AnsweringCode1
Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during TrainingCode1
PARM: A Paragraph Aggregation Retrieval Model for Dense Document-to-Document RetrievalCode1
Unsupervised Dense Information Retrieval with Contrastive LearningCode1
Large Dual Encoders Are Generalizable RetrieversCode1
Show:102550
← PrevPage 2 of 11Next →

No leaderboard results yet.