In this paper, we report the results of our participation in the TREC-COVID challenge. To meet the challenge of building a search engine for rapidly evolving biomedical collection, we propose a simple yet effective weighted hierarchical rank fusion approach, that ensembles together 102 runs from (a) lexical and semantic retrieval systems, (b) pre-trained and fine-tuned BERT rankers, and (c) relevance feedback runs. Our ablation studies demonstrate the contributions of each of these systems to the overall ensemble. The submitted ensemble runs achieved state-of-the-art performance in rounds 4 and 5 of the TREC-COVID challenge.
@article{arxiv.2010.00200,
title = {RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble},
author = {Michael Bendersky and Honglei Zhuang and Ji Ma and Shuguang Han and Keith Hall and Ryan McDonald},
journal= {arXiv preprint arXiv:2010.00200},
year = {2020}
}