Results 11 to 20 of about 41,352 (256)
Online Distillation for Pseudo-Relevance Feedback [PDF]
arXiv.org, 2023 Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and documents. In this paper, we explore a departure from this offline distillation strategy by investigating whether a ...
MacAvaney, Sean, Wang, Xi
openaire +3 more sources
A Study of Word Bigrams for Pseudo-relevance Feedback in Information Retrieval [PDF]
Journal of Universal Computer ScienceTraditional information retrieval models mostly adopt a term independence assumption and are based on single terms or unigrams. Past efforts have attempted to go beyond this assumption, such as by using contiguous terms (i.e.
Edward Kai Fung Dang +2 more
doaj +4 more sources
Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval [PDF]
Proceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval, 2021 10 ...
Wang, Xiao +3 more
openaire +4 more sources
End-to-end vertical web search pseudo relevance feedback queries recommendation software
SoftwareXUsers' web information needs are increasingly exploratory, seeking to navigate unfamiliar domains and discover knowledge. However, existing search engines struggle with ambiguous queries, leading to irrelevant results.
Tajmir Khan +4 more
doaj +2 more sources
Generalized Pseudo-Relevance Feedback
arXiv.orgQuery rewriting is a fundamental technique in information retrieval (IR). It typically employs the retrieval result as relevance feedback to refine the query and thereby addresses the vocabulary mismatch between user queries and relevant documents.
Tu, Yiteng +6 more
openaire +3 more sources
Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback [PDF]
International Conference on Information and Knowledge Management, 2021 Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and documents, a ...
HongChien Yu +2 more
semanticscholar +1 more source
Offline Pseudo Relevance Feedback for Efficient and Effective Single-pass Dense Retrieval [PDF]
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023 Dense retrieval has made significant advancements in information retrieval (IR) by achieving high levels of effectiveness while maintaining online efficiency during a single-pass retrieval process.
Xueru Wen +4 more
semanticscholar +1 more source
Journal of Information Science Theory and Practice, 2021 Pseudo relevance feedback (PRF) is a powerful query expansion (QE) technique that prepares queries using the top k pseudo-relevant documents and choosing expansion elements.
Farhan Yasir Hadi +3 more
doaj +1 more source
Pseudo Relevance Feedback with Deep Language Models and Dense Retrievers: Successes and Pitfalls [PDF]
ACM Trans. Inf. Syst., 2021 Pseudo Relevance Feedback (PRF) is known to improve the effectiveness of bag-of-words retrievers. At the same time, deep language models have been shown to outperform traditional bag-of-words rerankers.
Hang Li +4 more
semanticscholar +1 more source
ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval
ACM Transactions on the Web, 2022 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 ...
Xiao Wang +3 more
semanticscholar +1 more source