Hi Rafa To use the disambiguation engine you will need to tweak the parameters for the EntityhubLinkingEngine. The relevant parameters are
* Min Label Match Score "org.apache.stanbol.enhancer.engines.keywordextraction.minLabelMatchFactor" * Min Matched Tokens "org.apache.stanbol.enhancer.engines.keywordextraction.minFoundTokens" see [1] for the documentation from the Documentation: If used in combination with an disambiguation Engine one might want to consider to suggest Entities where only a single token of multi-token labels do match. In such cases a configuration like Min Matched Tokens=1 and Min Label Match Score <= 0.5 (e.g. 0.4) might be considered. With such scenarios users will also want to considerable increase the value for Max Suggestions (typically values > 10). I would suggest that you start of with "minLabelMatchFactor=0.33" and "minFoundTokens=1". In addition I would set the number of suggestions to ~20. best Rupert [1] http://stanbol.apache.org/docs/trunk/components/enhancer/engines/entitylinking#entity-linker-configuration On Tue, Dec 18, 2012 at 3:46 PM, Rafa Haro <[email protected]> wrote: > Hi all, > > I have been trying to use disambiguation-mlt engine with the new EntityHub > Linking Engine for Spanish. My goal is to link and disambiguate with any > kind of entity within the EntityHub, not only with Named Entities. So, I > have configured a new Enhancement Chain including only language detection, > OpenNlpSentenceDetectionEngine, OpenNlpTokenizerEngine, EntityLinkingEngine > and Disambiguation-mlt (installing the bundle version 0.10). After a few > tests, the disambiguation engine is working but is not able to disambiguate > anything. Removing the disambiguation engine from the Enhancement Chain we > have find out that only one candidate for each detected entity is given. > Therefore I think that maybe the disambiguation engine is working fine but > actually doesn't need to disambiguate anything due to only one candidate is > being passed to it from entityHub linking engine. > > What can be happening? Our suggestions parameter is set to 5 > > Thanks. Regards > > This message should be regarded as confidential. If you have received this > email in error please notify the sender and destroy it immediately. > Statements of intent shall only become binding when confirmed in hard copy > by an authorised signatory. > > Zaizi Ltd is registered in England and Wales with the registration number > 6440931. The Registered Office is 222 Westbourne Studios, 242 Acklam Road, > London W10 5JJ, UK. -- | Rupert Westenthaler [email protected] | Bodenlehenstraße 11 ++43-699-11108907 | A-5500 Bischofshofen
