Experiments on Semantic-based Clustering for Cross-document Coreference

We describe clustering experiments for cross-document coreference for the first Web People Search Evaluation. In our experiments we apply agglomerative clustering to group together documents potentially referring to the same individual. The algorithm is informed by the results of two different summarization strategies and an offthe-shelf named entity recognition component. We present different configurations of the system and show the potential of the applied techniques. We also present an analysis of the impact that semantic information and text summarization have in the clustering process.