An exploration of learning to link with Wikipedia: features, methods and training collection

We describe our participation in the Link-the-Wiki track at INEX 2009. We apply machine learning methods to the anchor-to-best-entry-point task and explore the impact of the following aspects of our approaches: features, learning methods as well as the collection used for training the models. We find that a learning to rank-based approach and a binary classification approach do not differ a lot. The new Wikipedia collection which is of larger size and which has more links than the collection previously used, provides better training material for learning our models. In addition, a heuristic run which combines the two intuitively most useful features outperforms machine learning based runs, which suggests that a further analysis and selection of features is necessary