A context‐dependent relevance model

Abstract

Numerous past studies have demonstrated the effectiveness of the relevance model (RM) for information retrieval (IR). This approach enables relevance or pseudo-relevance feedback to be incorporated within the language modeling framework of IR. In the traditional RM, the feedback information is used to improve the estimate of the query language model. In this article, we introduce an extension of RM in the setting of relevance feedback. Our method provides an additional way to incorporate feedback via the improvement of the document language models. Specifically, we make use of the context information of known relevant and nonrelevant documents to obtain weighted counts of query terms for estimating the document language models. The context information is based on the words (unigrams or bigrams) appearing within a text window centered on query terms. Experiments on several Text REtrieval Conference (TREC) collections show that our contextdependent relevance model can improve retrieval performance over the baseline RM. Together with previous studies within the BM25 framework, our current study demonstrates that the effectiveness of our method for using context information in IR is quite general and not limited to any specific retrieval model.

Query expansion techniques for information retrieval: A survey

“…Actually, the primary objectives of entity linking are to map a string in a document to its entity in knowledge base and to recognize the disambiguating context inside the knowledge base. Recently, Dang et al [80] proposed a context-dependent relevance model that provides an approach to incorporate the feedback through improvement of document language models. For evaluating document language models, it uses the context information on the relevant or irrelevant documents to obtain the weight counts (using BM25 weights [232,229]) of the individual query terms.…”

Research Project Submission before Graduation: Knowing its Importance and Understanding among Students and Learners

“…A study of a library's physical space must include some consideration for the research and information-seeking activities that users conduct in Knowing its Importance and Understanding among Students and Learners CHRISTOPHER M. LEE that space, which will be different depending on details such as the type and size of the library as well as the population it serves [11]. Researchers who create algorithms or implement other method to improve the effectiveness of information retrieval systems must have some understanding of the needs and behaviors of the system's front-end users [12].…”