Abstract
Searching relevant articles from medical resources is an important search task in clinical decision support system. The technical contents and long length of biomedical articles make this search task more complicated than many other search tasks. Previous research on biomedical information retrieval (IR) is typically based on keyword search. In this paper we propose a new approach. Using our approach, a user can use the full article as a query. This reduces the burden on the users and generates an effective automatic query from many more useful search features. In this novel search scenario, we explore in detail several important factors for developing a successful biomedical articles retrieval system, especially focusing on how to automatically convert an article into an effective search query. Specifically, we evaluate the performance of single features with different parameter configurations, as well as combinations of these features using the techniques of learning to rank and rank fusion. Experimental results on PubMed collection show that the introduction field is the most useful feature for transforming a query. Furthermore, our experiments showed that combining multiple features can significantly improve the effectiveness of a search system. (C) 2020 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Computers and Artificial Intelligence, Cairo University.