software

Named Entity Recognizer and Classifier takes care of identification of relevant entities - names of people, places,artworks, etc. The matching of candidate terms is realized by means of the FSA technology. The data for each particular category is stored in a separate file. A joint list iscompiled into a FSA that includes all terms together with theirsubcategorization.

The disambiguation phase takes into account a context in which aparticular NE candidate string appeared decides whether it reallycorrespond to an entity in question.

Relation extractor identifies textual fragments that express aparticular relation between two or more entities (or values). It canwork on a simple PoS-tagged data but it can also ask the Parserpackage to analyse the particular piece of text in question. Relationtriggers - specific expressions that signal that a relation holds - form key elements ofthe identification. A CRF classifier is further employed to markbeginnings and ends of particular elements appearing in the relation.

Decipher, NER, IE

14. 12. 2012

www.fit.vutbr.cz/~iotrusina/Decipher_NER+IE.tar.gz

K využití výsledku jiným subjektem je vždy nutné nabytí licence

Poskytovatel licence na výsledek nepožaduje licenční poplatek

https://www.fit.vut.cz/research/product/287/