DAMSEL: The DSTO/Macquarie System for Entity-Linking

This paper describes the DSTO/Macquarie University System for Entity Linking (DAMSEL), which competed in the 2009 Text Acquisition Conference Knowledge Base Population task. The system achieves 73.5% accuracy. For a given named entity mention, the system selects a set of candidate entities from the knowledge base and selects the most likely candidate based on the similarity between the document in which the mention was found and the candidate’s Wikipedia article. The best-performing candidate selection strategy took advantage of Wikipedia redirection and disambiguation data. The best-performing similarity measure was the cosine metric.