Relevance feedback in information retrieval

By J. Rocchio. 1971

Subfields: Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, methodology): “In relevance feedback, the representation of the user’s query is augmented with terms derived from documents that are known to be relevant (for example, documents that have been presented to the user and that the user has indicated is relevant): two popular formulations are based on the vector space”
Generation-Augmented Retrieval for Open-Domain Question Answering (2020, methodology): “GAR shares some merits with QE methods based on pseudo relevance feedback (Rocchio, 1971; AbdulJaleel et al., 2004; Lv and Zhai, 2010) in that both augment the queries with relevant contexts (terms).”
Document Expansion by Query Prediction (2019, background): “Approaches to tackling the vocabulary mismatch problem within these constraints include relevance feedback (Rocchio, 1971), query expansion (Voorhees, 1994; Xu and Croft, 2000), and modeling term relationships using statistical translation (Berger and Lafferty, 1999).”
Boosting Search Engines with Interactive Agents (2021, positive): “Most notably, we develop a self-supervised learning scheme for generating high-quality search session data, by exploiting insights from relevance feedback (Rocchio, 1971), used to train a supervised LM search agent based on T5 (Raffel et al.”
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (2019, neutral): “We compare with two widely used PRF models — The Rocchio’s algorithm on top of the TF-IDF retrieval model (PRF-TFIDF) (Rocchio, 1971) and the relevance model (RM3) based on the”
Scene Classification Via pLSA (2006, methodology): “The vector moving strategy uses the Rocchio’s formula [13].”
Personalized query expansion for the web (2007, methodology): “First approaches were manual [ 28 ] in the sense that the user was the one choosing the relevant results, and then various methods were applied to extract new terms, related to the query and the selected documents.”
Facing the cold start problem in recommender systems (2014, unknown): “In literature, one can find the following techniques adopted in RSs: (a) Collaborative filtering (CF) methods (Tso-Sutter, Marinho, & Schmidt-Thieme, 2008; Das et al., 2007; Sarvar et al., 2001; Schafer, Frankowski, Herlocker, & Sen, 2007; Jambor & Wang, 2010; Jin, Si, & Zhai, 2006; Wang, de Vries, ”
MatchMiner: Efficient Spanning Structure Mining in Large Image Collections (2012, methodology): “This step employs Rocchio’s relevance feedback [14] to improve the quality of retrieval results.”
ReQ-ReC: high recall retrieval with query pooling and interactive classification (2014, methodology): “To establish a baseline for performance comparison, we choose Rocchio’s method [15], by which the next query is selected according to Equation 1: ~qi = α~q0 + β 1 |Dr| ∑ ~dj∈Dr ~dj − γ 1 |Dnr| ∑ ~dk∈Dnr ~dk, (1) where ~q0 is the original query vector, Dr and Dnr are the set of known relevant and non”
Entity query feature expansion using knowledge base links (2014, background): “Query expansion techniques have been well studied for many models [23, 12, 31, 24, 37].”
Structure-Augmented Keyphrase Generation (2021, methodology): “…feedback be-tween each keyphrase r j ∈ R and X , we can adopt zero-shot query log synthesis (Ma et al., 2021), by using pseudo -relevance feedback (Rocchio, 1971): We treat supporting documents S r j as feedback documents with pseudo-relevance to r j , to connect r j with X using top-M…”
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing (2018, unknown): “To do so, we use the Rocchio’s relevance feedback algorithm [41] for vector space models.”
Combining classifiers in text categorization (1996, background): “ and nonrelevant documents [ 22 , 24].”
Evaluation of contextual information retrieval effectiveness: overview of issues and research (2010, background): “The ﬁrst attempts addressed in IR to improve the information retrieval performance are based on query reﬁnement using relevance feedback techniques [85] and word sense disambiguation techniques [112].”