BESearch: A Supervised Learning Approach to Search for Molecular Event Participants

Biomedical researchers rely on keyword-based search engines to retrieve superficially relevant documents, from which they must filter out irrelevant information manually. Hence, there is an urgent need for a more efficient system to help them rapidly locate specific molecular events and the participants involved in these events. In this paper, we propose a novel search system with a new search interface and answer ranking scheme. Due to the limited number of query types in the Biomedical-specific searches, we employ a form-based interface with various query templates for specifying required information. This can ascertain a user's intentions more accurately than a conventional keyword-based interface. Ranking is another key issue in this type of search. We propose a linear ranking model, trained by a supervised learning algorithm, which combines different features. Two semantic features, named entity types and semantic roles, are incorporated into the model to help match a query with entities in relevant documents. After employing all effective semantic features, our system achieves a Top-1 accuracy of 43.1% and Top-5 MRR of 47.1%. In comparison with the baseline system. Top-1 accuracy and Top-5 MRR increase by 9.5% and 7.1%.