Investigating Retrieval Method Selection with Axiomatic Features

TL;DR

This paper introduces a meta-learning approach for selecting and combining retrieval methods in ad-hoc information retrieval, using features based on IR axioms to improve relevance scoring.

Contribution

It proposes a novel meta-learner that predicts how to combine retrieval methods based on axiomatic features, enhancing retrieval performance.

Findings

Meta-learner often outperforms individual retrieval methods

Features based on IR axioms effectively inform method combination

Analysis reveals insights into the meta-learner's decision process

Abstract

We consider algorithm selection in the context of ad-hoc information retrieval. Given a query and a pair of retrieval methods, we propose a meta-learner that predicts how to combine the methods' relevance scores into an overall relevance score. Inspired by neural models' different properties with regard to IR axioms, these predictions are based on features that quantify axiom-related properties of the query and its top ranked documents. We conduct an evaluation on TREC Web Track data and find that the meta-learner often significantly improves over the individual methods. Finally, we conduct feature and query weight analyses to investigate the meta-learner's behavior.