-~-The Cow of Darkness-~-
If you see the image I am online 
Would a neural network work for natural language proccessing?
Author
I was thinking of inputting ech character of what the user sais into the neural net and having it output an intellegent response, but I''m not sure how well this would work. Any advice?
-~-The Cow of Darkness-~-
If you see the image I am online
-~-The Cow of Darkness-~-
If you see the image I am online
That would be a huge neural net! And I doubt back propagation could work on that either....so theoretically yes, practically no.
Brian J
Brian J
Author
Perhaps it would work better with each word (having an ID) were inputted? Or would it still be too huge?
With a VERY limited vocabulary, you might just be able to get that to work...nothing fancy though
Brian J
Brian J
Author
Ahh well... it''s worth trying anyway just so I can learn about what works and what doesn''t.
Speaking as someone quite knowledgeable about natural language processing (NLP), a simple neural net isn''t even going to produce acceptable outputs without being unbearably complex. Moreover, it''s a task that cannot be accomplished even with current cutting-edge NLP technology.
You may want to consider somehow limiting the range of possible inputs the player can produce, because otherwise the scope of the problem is so great as to make it intractable.
Anthony Serrano
You may want to consider somehow limiting the range of possible inputs the player can produce, because otherwise the scope of the problem is so great as to make it intractable.
Anthony Serrano
Author
OK... even though I know what to expect, I''m still going to try it and make it work as well as I can, just to get a better understanding of how neural nets work.
Without a clearer goal to aim for, I fear you''re not going to achieve anything. A neural net just maps inputs to outputs and you''re going to need to think carefully about how you''re classifying the inputs, what potential outputs you have, and how to judge the quality of the chosen outputs in order to train the net.
[ MSVC Fixes | STL Docs | SDL | Game AI | Sockets | C++ Faq Lite | Boost
Asking Questions | Organising code files | My stuff | Tiny XML | STLPort]
[ MSVC Fixes | STL Docs | SDL | Game AI | Sockets | C++ Faq Lite | Boost
Asking Questions | Organising code files | My stuff | Tiny XML | STLPort]
I second Kylotan''s comment. Try something simpler.
If you haven''t already read them, try the tutorials at my website, they should help your understanding.
ai-junkie.com
If you haven''t already read them, try the tutorials at my website, they should help your understanding.
ai-junkie.com
It''s a final no for me. I just do not believe in all these "let''s do neural networks to simulate how the brain gets intelligent".
To look at the best stuff done in this area (interpretation, memorisation, action), search the web for dmap, raps, mops, case based reasoning...
http://tfpsly.planet-d.net/english/ai.html
http://www.iit.edu/~sarimar/ai/index.html
To look at the best stuff done in this area (interpretation, memorisation, action), search the web for dmap, raps, mops, case based reasoning...
http://tfpsly.planet-d.net/english/ai.html
http://www.iit.edu/~sarimar/ai/index.html
This topic is closed to new replies.
Advertisement
Popular Topics
Advertisement