Exploring task-based query expansion at the TREC-COVID track

TL;DR

This paper investigates task-based query expansion for improving search results in the TREC-COVID track, focusing on identifying search tasks, classifying queries, and comparing expansion methods to enhance ranking effectiveness.

Contribution

It introduces a method for task-based query expansion and demonstrates its potential to improve search rankings over standard BM25 baselines.

Findings

Query expansion using task terms slightly improves NDCG@20 scores.

Manual classification of search queries by tasks is feasible.

Further gains possible with more specific task identification.

Abstract

We explore how to generate effective queries based on search tasks. Our approach has three main steps: 1) identify search tasks based on research goals, 2) manually classify search queries according to those tasks, and 3) compare three methods to improve search rankings based on the task context. The most promising approach is based on expanding the user's query terms using task terms, which slightly improved the NDCG@20 scores over a BM25 baseline. Further improvements might be gained if we can identify more specific search tasks.