HITS' Monolingual and Cross-lingual Entity Linking System at TAC 2013
Angela Fahrni, Benjamin Heinzerling, Thierry Göckel, Michael Strube · 2013
This paper presents HITS ’ system for mono-lingual and cross-lingual entity linking at TAC 2013. The system is an extended version of our last year’s joint entity disambiguation and clustering system based on Markov Logic Networks. We describe the new extensions and discuss the results. The results show that our approach is com-petitive across all three languages: with a micro-average accuracy of 0.817, our best En-glish run is close to the one of the best sys-tem (0.833). While we had the best perform-ing system in the Spanish cross-lingual en-tity linking task, our Chinese results are lower than the ones of the best system. 1