IRIT at TREC Knowledge Base Acceleration 2013: Cumulative Citation Recommendation Task

Abstract

This paper describes the IRIT lab participation to the Cumulative Citation Recommendation task of the TREC 2013 Knowledge Base Acceleration Track. In this task, we are asked to implement a system which aims to detect “Vital” documents that a human would want to cite when updating the Wikipedia article for the target entity. Our approach is built on two steps. First, for each topic (entity), we retrieve a set of potential relevant documents containing at least one entity mention. These documents are then classified using a supervised learning algorithm to identify which ones are vital. We submitted three runs using different combinations of features. Obtained results are presented and discussed.