Named entity linking in microblog posts using graph-based centrality scoring

Microblogging platforms have emerged as large collections of short documents, which have been growing in term of size and volume. In fact, providing an effective way to add semantics to this form of communication present a significant research challenge because his noisy and inconsistency nature. Named Entity Linking (NEL) is a subtask of information extraction that aims to ground entity mentions to their corresponding node in a Knowledge Base (KB), which requires a disambiguation step, because many resources can be matched to the same entity that lead to synonymy and polysemy problems. To overcome such problems especially in the context of short text, we present a robust system for automatically extract named entities, disambiguating and linking them to knowledge base resources, based on graph centrality algorithm and Linked Open Data (LOD) paradigm. Also, we evaluate our system using a real Twitter dataset [1] and comparing it with a public tool to show his effectiveness.