Document Language Models, Query Models, and Risk Minimization for Information Retrieval

By John D. Lafferty, Chengxiang Zhai. 2001

193 citations recorded by the source corpus.

Subfields: Information Systems, Signal Processing

How researchers see this paper

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

In Information Systems

In Signal Processing

Citations in the corpus

Relevance-based Word Embedding (2017, methodology): “We retrieve the documents for the expanded query language model using the KL-divergence formula [18] with Dirichlet prior smoothing (μ = 1500) [45].”
An Introduction to Neural Information Retrieval (2018, unknown): “The underlying approach to scoring a document in RM is by computing the KL divergence [Lafferty and Zhai, 2001] between the query language model θq and the document language model θd.”
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations (2019, methodology): “cument Retrieval Model Here,wedescribethemodelthatweusetoretrievedocumentsgiven a query, conversation context, and current clarifying question as wellasuser’sanswer.WeusetheKL-divergenceretrievalmodel[24] based on the language modeling framework [30] with Dirichlet prior smoothing [52] where we line”
Pseudo-Relevance Feedback Based on Matrix Factorization (2016, methodology): “For the language modeling framework, we employed the KL-divergence retrieval model [13] with the Dirichlet prior smoothing method.”
Complementing Lexical Retrieval with Semantic Residual Embedding (2020, methodology): “Traditionally, information retrieval has relied on lexical retrieval models such as BM25 (Robertson and Walker, 1994) and query likelihood (Lafferty and Zhai, 2001) for their efﬁciency and effectiveness.”
SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval (2020, methodology): “Later proposed methods, such as [7], [18], [16], did not show much advantage over BM25.”
COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List (2021, methodology): “Lexical Retriever Classical IR systems rely on exact lexical match retrievers such as Boolean Retrieval, BM25 (Robertson and Walker, 1994) and statistical language models (Lafferty and Zhai, 2001).”
Semantic Matching by Non-Linear Word Transportation for Information Retrieval (2016, background): “The key difficulty of these models is how to formalize and estimate the translation probabilities between words [19, 15].”
A Study of Smoothing Methods for Language Models Applied to Ad Hoc Information Retrieval (2001, methodology): “We now show that the two-stage smoothing method can also be formally derived using the risk minimization retrieval framework proposed in [Lafferty and Zhai 2001].”
Direct Learning to Rank and Rerank (2018, background): “…ranking water pipes in order of vulnerability (as considered by Li et al, 2013), other areas of information retrieval (Xu, 2007; Cao et al, 2007; Matveeva et al, 2006; Lafferty and Zhai, 2001; Li et al, 2007) and in almost any domain where one measures the quality of results by rank statistics.”
Document Retrieval Using Entity-Based Language Models (2016, methodology): “We rank document d by the cross entropy between the language models induced from the query (q) and d [25]:”
Beyond [CLS] through Ranking by Generation (2020, background): “On the other hand, classical literature on probabilistic models for IR showed that language modeling, a type of simple generative model, can be effective for document ranking (Zhai, 2008; Lafferty and Zhai, 2001; Ponte and Croft, 1998).”
Embedding-based Query Language Models (2016, methodology): “We employed the KL-divergence retrieval model [14] with the Dirichlet prior smoothing method.”