Entity Mention Normalization System

Jump to navigation Jump to search

An Entity Mention Normalization System is a Normalization System that can solve an Entity Mention Normalization Task.



  • (Kulkarni et al., 2009) ⇒ Sayali Kulkarni, Amit Singh, Ganesh Ramakrishnan, Soumen Chakrabarti. (2009). “Collective Annotation of Wikipedia Entities in Web Text.” In: Proceedings of ACM SIGKDD Conference (KDD-2009). doi:10.1145/1557019.1557073.
    • QUOTE: The first Web-scale entity disambiguation system was SemTag [5]. SemTag annotated about 250 million Web pages with IDs from the Stanford TAP entity catalog [8]. The basic technique was to compare the surrounding context of a spot s with text metadata associated with candidate entity γ in TAP. SemTag preferred high precision over recall, proposing only about 450 million annotations, i.e., fewer than two annotations per page on average.