Frugal neural reranking: evaluation on the Covid-19 literature

Tiago Almeida, Sérgio Matos

Keywords: Neural information retrieval, Literature search, Relevance feedback, TREC Covid

TL;DR: A lightweight IR pipeline applied to the novel coronavirus literature and evaluated on the TREC Covid challenge

Abstract:

The Covid-19 pandemic urged the scientific community to join efforts at an unprecedented scale, leading to faster than ever dissemination of data and results, which in turn motivated more research works. This paper presents and discusses information retrieval models aimed at addressing the challenge of searching the large number of publications that stem from these studies.

The model presented, based on classical baselines followed by an interaction based neural ranking model, was evaluated and evolved within the TREC Covid challenge setting. Results on this dataset show that, when starting with a strong baseline, our light neural ranking model can achieve results that are comparable to other model architectures that use very large number of parameters.