SCM - Entity Classification with WordNet similarity measures

Semantic Concept Mapping (SCM) maps the noun phrases representing the entities as well as the target classes to WordNet. Graph-based WordNet similarity measures are used to assign the closest class to the noun phrase. If a noun phrase does not match any WordNet concept, a Targeted Hypernym Discovery (THD) algorithm is optionally executed. The THD algorithm extracts a hypernym from a Wikipedia article defining the noun phrase using lexico-syntactic patterns. This hypernym is then used to map the noun phrase to a WordNet synset.

Demo

  • Web interface for older implementation
    • implements entity extraction - the input text is parsed for entities
    • the list of target classes is a list of WordNet entries, synset references (i.e. #1 is not supported)
    • The THD integration is broken. Entities, which cannot be resolved to WordNet entries, will be skipped. Uncheck "use Wikipedia" for faster processing
    • JWNL support is broken
  • SCM (i.e. WordNet similarity measures) are implemented within our newer BOA classifier