Hi Eldad
   I want to mention a new OpenNLP contribution 'Similarity' which parses 
question and answer and use parsing results to do a better match to filter out 
irrelevant answers.   This component does not do what you are describing 
directly, it does not have 'semantic' tagging as you describe, but it is 
domain-independent and assures relevance in any search domain.
   Once OpenNLP does parsing in  German, French etc Similarity would work.
RegardsBoris





> Date: Sun, 20 Nov 2011 09:34:19 +0200
> Subject: Search engine using OpenNLP
> From: [email protected]
> To: [email protected]
> 
>  HI,
> I'm wondering if anyone had an experience with using OpenNLP as a
> search engine input parser.
> 
> For example, let's imagine that a restaurant wants to have a
> search engine in their site. their users can write things like:
> "Pizza to 12:00, delivery to my house at London" -> food: pizza, time:
> 12:00, order type: delivery, location: London"
> "Pasta, Apple pie, reservation, 14:00 (outside/smoking)." -> food: pasta,
> apple pie, time:14:00, order type: reservation, location: outside"
> "Smoking area, reservation to 12:00" -> "order type: reservation: , time:
> 12:00, location: outside/smoking area"
> 
> In addition, it should be multilingual (I.e. German, French etc).
> I have the entities translated into different languages (I.e EN:reservation
> -> FR:réservation).
> 
> Please advise.
> Thanks!
                                          

Reply via email to