A Unified Relevance Retrieval Model by Eliteness Hypothesis

TL;DR

This paper introduces a unified relevance retrieval model based on the Eliteness Hypothesis, which leverages deterministic relationships between term eliteness and relevance to improve information retrieval by integrating relevance information from both documents and queries.

Contribution

It proposes a novel theoretical framework for retrieval that unifies existing models and utilizes relevance information from both documents and queries.

Findings

Preliminary experiments show promising potential of the proposed ranking function.

The model offers a unified approach capable of integrating relevance data from documents and queries.

Theoretical foundation based on the Eliteness Hypothesis enhances retrieval effectiveness.

Abstract

In this paper, an Eliteness Hypothesis for information retrieval is proposed, where we define two generative processes to create information items and queries. By assuming the deterministic relationships between the eliteness of terms and relevance, we obtain a new theoretical retrieval framework. The resulting ranking function is a unified one as it is capable of using available relevance information on both the document and the query, which is otherwise unachievable by existing retrieval models. Our preliminary experiment on a simple ranking function has demonstrated the potential of the approach.