HI Guys,

I’m beginner in AI / bot area. I’m on the stage of exploring technique used by pros and hobbyists that are already available. Things like DBPedia,Wordnet, WN SQL Builder, NLP parsers etc.
What I’m missing however is knowledge regarding context and topics, precisely how bot can understand subject / context of sentence ?
The other thing is once bot understand or interpret subject then how bot should answer ? I quess there are many possible ways but how to define scope of answers to make conversation “flowing”?
I’m Java programming (amateur) and this would be language that I’m going to use to build Bot. So if there are any free libraries available please let me know. 
Like I stated above I’m on the early research stage to get to know what is available already so I won’t have to reinvent the wheel.

Any help much appreciated.

BTW. As many before me, thanks founders and contributors of this page ! I’s great to have such big knowledge repository !

Evo

The place to start is AIML.  Once you understand how AIML works, and can get it working the way you want then you’re ready to move on to other methods.  ChatterBean and Program D are Java AIML interpreters.  It might be a good project to see if you can get either one working on Google App Engine.  If you do, publish a blog post about it, because others will be interested in how you did it. 

Pattern matching AI is not much different from data mining and sentiment analysis.  So, the next step would probably be to go with the popular Python NLTK Natural Language Toolkit.  Grammar parsing gets into shaky ground; because, there is no one right way to parse, or “understand”, natural language.  For instance, IBM Watson uses lots of different techniques in parallel, and then correlates all the results statistically, or probabilistically. 

The ultimate challenge today is working with semantic web data such as RDF, and being able to interact effectively with it in natural language.  For instance, IBM Watson uses structured data, such as triplestores, in order to figure out, or “understand”, parallel unstructured text.

I would also recommend taking a look at OpenEphyra, which is a question-answering framework written in Java.  If you are interested in a semantic / parsing approach, it has a lot of tools built-in.

Evonevo Evo - Mar 24, 2012:

BTW. As many before me, thanks founders and contributors of this page ! I’s great to have such big knowledge repository !

Welcome to the Chatbots.org forums Evo! Thanks for the compliments. Contributors are getting more active nowadays because lots is happening in our field. 2012 is the year! Good to see all this activity! Our contributors make this forum alive, they create the helpful atmosphere and they create the knowledge repository. All credits to them!... Please feel free to find your way around..