Pseudo-relevance Feedback For Multiple Representation Dense Retrieval

Abstract

Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set of retrieved documents, known as the pseudo-relevant set. Recently, dense retrieval -- through the use of neural contextual language models such as BERT for analysing the documents' and queries' contents and computing their relevance scores -- has shown a promising performance on several information retrieval tasks still relying on the traditional inverted index for identifying documents relevant to a query. Two different dense retrieval families have emerged: the use of single embedded representations for each passage and query (e.g. using BERT's [CLS] token), or via multiple representations (e.g. using an embedding for each token of the query and document). In this work, we conduct the first study into the potential for multiple representation dense retrieval to be enhanced using pse

Stats

• citations52
• S2 citations—
• github stars0
• HF likes0
• heat score12.93
• arxiv keywang2021pseudo

Related papers

• Improving Query Representations For Dense Retrieval With Pseudo Relevance Feedback (2021)12.10
• Improving Query Representations For Dense Retrieval With Pseudo Relevance Feedback: A Reproducibility Study (2021)7.16
• Investigating Multi-layer Representations For Dense Passage Retrieval (2025)0.00
• On Approximate Nearest Neighbour Selection For Multi-stage Dense Retrieval (2021)8.35
• Pseudo Relevance Feedback Is Enough To Close The Gap Between Small And Large Dense Retrieval Models (2025)0.00
• A Deep Learning Approach For Selective Relevance Feedback (2024)6.34
• Improving Document Representations By Generating Pseudo Query Embeddings For Dense Retrieval (2021)9.41
• TPRF: A Transformer-based Pseudo-relevance Feedback Model For Efficient And Effective Retrieval (2024)0.00