Modeling Diverse Relevance Patterns in Ad-hoc Retrieval

TL;DR

This paper introduces HiNT, a hierarchical neural matching model that adaptively assesses relevance at multiple granularities, improving ad-hoc retrieval effectiveness by capturing diverse relevance patterns.

Contribution

The paper presents a novel data-driven hierarchical neural model that combines local and global relevance signals, enabling adaptive relevance assessment in ad-hoc retrieval.

Findings

HiNT outperforms state-of-the-art models on benchmark datasets.

The hierarchical approach effectively captures diverse relevance patterns.

Experimental results show significant retrieval performance improvements.

Abstract

Assessing relevance between a query and a document is challenging in ad-hoc retrieval due to its diverse patterns, i.e., a document could be relevant to a query as a whole or partially as long as it provides sufficient information for users' need. Such diverse relevance patterns require an ideal retrieval model to be able to assess relevance in the right granularity adaptively. Unfortunately, most existing retrieval models compute relevance at a single granularity, either document-wide or passage-level, or use fixed combination strategy, restricting their ability in capturing diverse relevance patterns. In this work, we propose a data-driven method to allow relevance signals at different granularities to compete with each other for final relevance assessment. Specifically, we propose a HIerarchical Neural maTching model (HiNT) which consists of two stacked components, namely local matching layer and global decision layer. The local matching layer focuses on producing a set of local relevance signals by modeling the semantic matching between a query and each passage of a document. The global decision layer accumulates local signals into different granularities and allows them to compete with each other to decide the final relevance score. Experimental results demonstrate that our HiNT model outperforms existing state-of-the-art retrieval models significantly on benchmark ad-hoc retrieval datasets.