Finding Salient Context based on Semantic Matching for Relevance Ranking

TL;DR

This paper introduces a salient-context semantic matching approach that enhances relevance ranking by identifying and leveraging the most important contextual information within documents, demonstrated through TREC experiments.

Contribution

It proposes a novel salient-context concept and a method to locate and utilize it for improved relevance ranking in information retrieval.

Findings

Outperforms state-of-the-art relevance ranking methods

Effective in identifying salient contexts within documents

Improves retrieval accuracy on TREC datasets

Abstract

In this paper, we propose a salient-context based semantic matching method to improve relevance ranking in information retrieval. We first propose a new notion of salient context and then define how to measure it. Then we show how the most salient context can be located with a sliding window technique. Finally, we use the semantic similarity between a query term and the most salient context terms in a corpus of documents to rank those documents. Experiments on various collections from TREC show the effectiveness of our model compared to the state-of-the-art methods.