Named Entity Recognition

This site assembles a few local resources for Named Entity Recognition, plus selected links to external resources. Generally speaking, Named Entity Recognition is the task to identify a (usually small) set of semantic categories for entities known by their name only, including (but not limited to) LOCATION, PERSON, ORGANIZATION, TIME, and DATE.

• NERD core scheme, data categories for Named Entities, extracted from nerd.eurecom.fr (CC-BY)
• JRCNames2RDF, retrieves JRC Names from the web and creates a NERD-conformant RDF/XML dump
• JRC Names (external), highly multilingual named entity resource for person and organisation names
  • a large, automatically created Named Entity repository with currently more than 500,000 names of organizations and persons and their variants in Latin, Greek, Arabic, Cyrillic, Japanese and Chinese script
  • license conditions: free to use, but no derivatives
  • Reference: Steinberger Ralf, Bruno Pouliquen, Mijail Kabadjov, Jenya Belyaeva & Erik van der Goot (2011). JRC-Names: A freely available, highly multilingual named entity resource. Proceedings of the 8th International Conference Recent Advances in Natural Language Processing (RANLP). Hissar, Bulgaria, 12-14 September 2011.
  • Linking to DBpedia to be used with our extraction script
• Stanford Named Entity Recognizer (NER) (external), CRF-based classifier and modules for English and Chinese
  • German modules by Faruqui and Padó (2010)