HITS’ monolingual and cross-lingual entity linking system at TAC 2013

This paper presents HITS ’ system for mono-lingual and cross-lingual entity linking at TAC 2012. We propose a joint system for entity dis-ambiguation, recognition of NILs and cluster-ing using Markov Logic. The proposed model (1) is global, i.e. a group of mentions in a text is disambiguated in one single step combin-ing various global and local features, and (2) performs disambiguation, unknown entity de-tection and clustering jointly. The model for all languages is exclusively trained on English Wikipedia articles. The results achieved in the TAC monolingual and cross-lingual entity linking tasks show that our approach is competitive: our best En-glish run achieves 8.5 percent points above median, while we outperformed all other par-ticipating systems in the Chinese cross-lingual subtask. The results for the Spanish subtask are lower due to a bug. Our unofficial Spanish results (after fixing the bug) are close to the ones of the best system.