Forums before death by AOL, social media and spammers... "We can't have nice things"
|    comp.ai    |    Awaiting the gospel from Sarah Connor    |    1,954 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 1,149 of 1,954    |
|    Jorekunrin@gmail.com to All    |
|    Wanted advice on natural language for we    |
|    10 Aug 06 07:36:05    |
   
   Hi all,   
      
   I'm developing a location-based search engine for a few New York   
   neighborhoods and was hoping that I could get some advice on natural   
   language processing. Specifically, I'd like to figure out how to   
   answers questions like these:   
      
   1) "Where can I find the best pizza on the Upper West Side?"   
   For questions like this one, I would like the engine to respond by   
   searching for Upper West Side restaurants that users have rated highly   
   for their pizza.   
      
   2) "Where do I go to have fun this weekend?"   
   With questions like these, I would like the engine to use more   
   questions to figure out what the user wants to do to prepare (e.g. "Do   
   you want movie recommendations?" "Do you want restaurant   
   recommendations?"). Once the user answers a few of these questions, the   
   engine could give him specific recommendations. ("Yes? Well, here's   
   where this movie is playing in your neighborhood").   
      
   In both cases, the engine has to identify natural language patterns for   
   questions. It should also be able to process more technical search   
   query methods.   
      
   Anyone who wants more details or would like to give implementation   
   suggestions can contact me at jbo25@columbia.edu   
      
   Thanks,   
   John   
      
   [ comp.ai is moderated ... your article may take a while to appear. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)   
|
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca