English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Pseudo-Relevance Feedback (PRF) utilises the relevance signals from the top-kpassages from the first round of retrieval to perform a second round ofretrieval aiming to improve search effectiveness. A recent research directionhas been the study and development of PRF methods for deep language modelsbased rankers, and in particular in the context of dense retrievers. Denseretrievers, compared to more complex neural rankers, provide a trade-offbetween effectiveness, which is often reduced compared to more complex neuralrankers, and query latency, which also is reduced making the retrieval pipelinemore efficient. The introduction of PRF methods for dense retrievers has beenmotivated as an attempt to further improve their effectiveness.  In this paper, we reproduce and study a recent method for PRF with denseretrievers, called ANCE-PRF. This method concatenates the query text and thatof the top-k feedback passages to form a new query input, which is then encodedinto a dense representation using a newly trained query encoder based on theoriginal dense retriever used for the first round of retrieval. While themethod can potentially be applied to any of the existing dense retrievers,prior work has studied it only in the context of the ANCE dense retriever.  We study the reproducibility of ANCE-PRF in terms of both its training(encoding of the PRF signal) and inference (ranking) steps. We further extendthe empirical analysis provided in the original work to investigate the effectof the hyper-parameters that govern the training process and the robustness ofthe method across these different settings. Finally, we contribute a study ofthe generalisability of the ANCE-PRF method when dense retrievers other thanANCE are used for the first round of retrieval and for encoding the PRF signal.

Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study