Overview of TAC-KBP2015 Tri-lingual Entity Discovery and Linking

In this paper we give an overview of the Tri-lingual Entity Discovery and Linking task at the Knowledge Base Population (KBP) track at TAC2015. In this year we introduced a new end-to-end Tri-lingual entity discovery and linking task which requires a system to take raw texts from three languages (English, Chinese and Spanish) as input, automatically extract entity mentions, link them to an English knowledge base, and cluster NIL mentions across languages. More entity types and mention types were also added into some languages. In this paper we provide an overview of the task definition, annotation issues, successful methods and research challenges associated with this new task. This new task has attracted a lot of participants and has intrigued many interesting research problems and potential approaches. We believe it’s a promising task to be combined with Tri-lingual slot filling to form a new Tri-lingual cool-start KBP track in TAC2016.