Participation in TREC 2020 COVID Track Using Continuous Active Learning

TL;DR

This paper details participation in TREC 2020 COVID Track using Continuous Active Learning, achieving top scores and demonstrating the effectiveness of CAL in pandemic-related search tasks.

Contribution

The paper introduces the application of Continuous Active Learning (CAL) and its variations to improve search performance in COVID-19 literature retrieval tasks.

Findings

Achieved top scores among manual runs

Remained competitive across all submission categories

Validated CAL's effectiveness in pandemic search scenarios

Abstract

We describe our participation in all five rounds of the TREC 2020 COVID Track (TREC-COVID). The goal of TREC-COVID is to contribute to the response to the COVID-19 pandemic by identifying answers to many pressing questions and building infrastructure to improve search systems [8]. All five rounds of this Track challenged participants to perform a classic ad-hoc search task on the new data collection CORD-19. Our solution addressed this challenge by applying the Continuous Active Learning model (CAL) and its variations. Our results showed us to be amongst the top scoring manual runs and we remained competitive within all categories of submissions.