Entity Disambiguation for Knowledge Base Population

Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 277–285, Beijing, August 2010 Entity Disambiguation for Knowledge Base Population †Mark Dredze and †Paul McNamee and †Delip Rao and †Adam Gerber and ⋆Tim Finin †Human Language Technology Center of Excellence, Center for Language and Speech Processing Johns Hopkins University ⋆University of Maryland – Baltimore County mdredze,mcnamee,delip,adam.gerber@jhu.edu, finin@umbc.edu Abstract The integration of facts derived from information extraction systems into existing knowledge bases requires a system to disambiguate entity mentions in the text. This is challeng- ing due to issues such as non-uniform variations in entity names, mention ambiguity, and entities absent from a knowl- edge base. We present a state of the art system for entity dis- ambiguation that not only addresses these challenges but also scales to knowledge bases with several million entries using very little resources. Further, our approach achieves perfor- mance of up to 95% on entities mentioned from newswire and 80% on a public test set that was designed to include challenging queries. 1 Introduction The ability to identify entities like people, orga- nizations and geographic locations (Tjong Kim Sang and De Meulder, 2003), extract their at- tributes (Pasca, 2008), and identify entity rela- tions (Banko and Etzioni, 2008) is useful for sev- eral applications in natural language processing and knowledge acquisition tasks like populating structured knowledge bases (KB). However, inserting extracted knowledge into a KB is fraught with challenges arising from nat- ural language ambiguity, textual inconsistencies, and lack of world knowledge. To the discern- ing human eye, the “Bush” in “Mr. Bush left for the Zurich environment summit in Air Force One.” is clearly the US president. Further con- text may reveal it to be the 43rd president, George W. Bush, and not the 41st president, George H. W. Bush. The ability to disambiguate a polyse- mous entity mention or infer that two orthograph- ically different mentions are the same entity is crucial in updating an entity’s KB record. This task has been variously called entity disambigua- tion, record linkage, or entity linking. When per- formed without a KB, entity disambiguation is called coreference resolution: entity mentions ei- ther within the same document or across multi- ple documents are clustered together, where each cluster corresponds to a single real world entity. The emergence of large scale publicly avail- able KBs like Wikipedia and DBPedia has spurred an interest in linking textual entity references to their entries in these public KBs. Bunescu and Pasca (2006) and Cucerzan (2007) presented im- portant pioneering work in this area, but suffer from several limitations including Wikipedia spe- cific dependencies, scale, and the assumption of a KB entry for each entity. In this work we in- troduce an entity disambiguation system for link- ing entities to corresponding Wikipedia pages de- signed for open domains, where a large percent- age of entities will not be linkable. Further, our method and some of our features readily general- ize to other curated KB. We adopt a supervised approach, where each of …

Content truncated to 500 words