Transferring knowledge between topics in systematic reviews

Abstract

In the medical domain, a systematic review (SR) is a well-structured process aimed to review all available literature on a research question. This is however a laborious task, both in terms of money and time. As such, the automation of a SR with the aid of technology has received interest in several research communities, among which the Information Retrieval community. In this work, we experiment on the possibility of leveraging previously conducted systematic reviews to train a classifier/ranker which is later applied to a new SR. We also investigate on the possibility of pre-training Deep Learning models and eventually tuning them in an Active Learning process. Our results show that the pre-training of these models deliver a good zero-shot (i.e., with no fine-tuning) ranking, achieving an improvement of 79% for the MAP metric, with respect to a standard classifier trained on few in-domain documents. However, the pre-trained deep learning algorithms fail to deliver consistent results when continuously trained in an Active Learning scenario: our analysis shows that using smaller sized models and employing adapter modules might enable an effective active learning training.