Probability models for information retrieval based on divergence from randomness

By Gianni Amati. 2003

300 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/546b29236b79d02d720eb6ecefd3fddcd7a353e5

How researchers see this paper

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

1. Jimmy J. Lin
2. Craig Macdonald
3. Andrew Yates
4. Iadh Ounis
5. Zhi Zheng
6. Ben He
7. Kai Hui
8. Dwaipayan Roy

Citations in the corpus

• To Clean or Not to Clean (2018, methodology): “For a comprehensive discussion of DFR model, please refer to References [1, 2, 45].”
• Voting for candidates: adapting data fusion techniques for an expert search task (2006, methodology): “The remaining two weighting models tested are from the Divergence from Randomness (DFR) framework [1].”
• BERT-QE: Contextualized Query Expansion for Document Re-ranking (2020, methodology): “Unsupervised query expansion models, like Rocchio’s query expansion (Rocchio, 1971) with the KL divergence model (Amati, 2003), and RM3 (Lavrenko and Croft, 2001), are employed as a group of baseline models, wherein the query is expanded by selecting terms from top-ranked documents from the initial ”
• Terrier : A High Performance and Scalable Information Retrieval Platform (methodology): “For this purpose, we devised a parameter-free QE mechanism, called Bo1 [1, 11], as a default in Terrier.”
• From Puppy to Maturity: Experiences in Developing Terrier (2012, background): “For example, due to its modularity, Terrier allows various ways of changing the ranking of documents, providing a huge variety of weighting models, including Okapi BM25 [17], language modelling [10, 23] and a vast number of models from the Divergence from Randomness framework [2].”
• Query Expansion Techniques for Information Retrieval: a Survey (2017, unknown): “Some experimental studies suggested the addition of optimum number of expansion terms in the initial query [109,222,52,11,61,31,269,201,290](described briefly in Section 3.1.1 and in Zhai and Lafferty 2001 [286] Log-likelihood Franzoni and Milani 2012 [95], Franzoni 2017 [94] PMING distance Paik et…”