A probabilistic model of information retrieval: development and comparative experiments - Part 1

By Karen Spärck Jones, S. Walker, Stephen E. Robertson. Information Processing & Management, 2000

1,101 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c61e0bd909491f0a671fe91db6cccfa2ba1890da

How researchers see this paper

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

Citations in the corpus

Repository-Level Prompt Generation for Large Language Models of Code (2022, methodology): “RLPG-BM25: Instead of using PPC to rank prompt proposals, use the scores obtained by BM25 (Jones et al., 2000) to select the best prompt proposal.”
On the history of evaluation in IR (2008, methodology): “Using a further development of an old probabilistic model, we in the Okapi team developed a much extended version of RSJ weighting, now commonly known as (Okapi) BM25: this makes effective use of TF and also document length [32].”
Retrieving Textual Evidence for Knowledge Graph Facts (2019, methodology): “75, which are the default parameters optimized using the TREC dataset [13].”
A Study of Information Retrieval Weighting Schemes for Sentiment Analysis (2010, unknown): “95 respectively (Jones et al., 2000).”
Adapting boosting for information retrieval measures (2010, unknown): “2002) and the classical probabilistic retrieval model (Jones et al. 1998) on the ad hoc retrieval task using TREC test sets.”
Is searching full text more effective than searching abstracts? (2009, methodology): “• The Okapi bm25 ranking algorithm [35,36] (described in Section 5.”
Understanding inverse document frequency: on theoretical arguments for IDF (2004, methodology): “Then the measure proposed by Sparck Jones, as a weight to be applied to term t i , is essentially idf (t i ) = log N n i (1) Actually this is not quite accurate – the original measure was an integer approximation to this formula, and the logarithm was specifically to the base 2.”
Have things changed now?: an empirical study of bug characteristics in modern open source software (2006, methodology): “To solve this problem, we apply information retrieval techniques [22] on the bug database to retrieve the specific category of bugs.”
Cross-Domain Sentence Modeling for Relevance Transfer with BERT (2019, methodology): “Building on the BIM, Okapi BM25 (commonly dubbed BM25) weighting was introduced to address the need for such a probabilistic model without introducing too many additional parameters [28].”
Incorporating External Knowledge through Pre-training for Natural Language to Code Generation (2020, methodology): “We use the BM25 retrieval algorithm (Jones et al., 2000) implemented in ElasticSearch.4 We take this frequency and calculate the probability distribution after smoothing with a temperature τ ∈ [1,∞]: P (y) = freq(y)1/τ/ ∑ y′∈DAPI freq(y′)1/τ As τ changes from 1 to ∞, P (y) shifts from a…”
Quality evaluation of product reviews using an information quality framework (2011, methodology): “Given a user query, the first phase computes the content similarity between the query and every blog entry in terms of the Okapi BM-25 IR model [14].”
Mining Query Logs: Turning Search Usage Data into Knowledge (2010, methodology): “In the experiments performed by the authors they used the Okapi BM25 [119] scoring function.”