software

Semantic Annotator is based on a Named Entity Recognizer which takes care of identification of relevant entities - names of people, places, etc. The matching of candidate terms is realized by means of the FSA technology. The data for each particular category is stored in the knowledge base. A joint list is compiled into a FSA that includes all terms together with their subcategorizations. The disambiguation phase takes into account a context in which a particular NE candidate string appeared and decides whether it really corresponds to an entity in question. The system includes also the coreference resolution modul.

NER, named entity recognition

1. 12. 2014

http://www.fit.vutbr.cz/research/prod/index.php?id=406

K využití výsledku jiným subjektem je vždy nutné nabytí licence

Poskytovatel licence na výsledek nepožaduje licenční poplatek

http://www.fit.vutbr.cz/research/prod/index.php?id=406