XPost: comp.lang.lisp, comp.lang.prolog   
   From: nobody@nowhere.com   
      
   S White wrote :   
      
   > Hi,   
   > Just wanted to ask some advice. My plan is to research the area of AI   
   > and law, specifically by developing a prototype for decision support   
   > system adjusted to particular legislation etc. As i'm a lawyer rather   
   > than a technician i am not yet that skilled in the area of ai   
   > programming but hopefully i'll improve. The main question is what   
   > language (prolog or lisp) should i use to start the work? What i   
   > mainly want to do at the moment is to create a program with which you   
   > can converse in natural language and "build upon" it until it reaches   
   > rather high sophistication. When I achieve a program capable of rather   
   > general conversation (and also know more about ai) i plan to add the   
   > legal reasoning part. What is your suggestion on how to go about this?   
   > (It's a four year project so i know this wont happen overnight).   
   > Ultimately i want to complement the program with some kind of good   
   > interface (possible face with lip sync / speech synthesis).   
   >   
   > Regards,   
   > S   
      
   This is a very ambitious project.   
   Even though you have allowed yourself 4 years, I don't know if you can do it   
   in that time, because creating a program that can converse in natural   
   language is extremely difficult.   
      
   I'm working on such a project myself.  But I've been working on this project   
   for many years, and I may well be working on it for the next ten years too.   
   Natural Language Processing is not easy.   
      
   I recommend that you use Prolog rather than Lisp.  Prolog is said to be   
   better for NLP than Lisp.  Among other reasons, it has something called   
   "DCG grammar" features.  (In other words it has facilities for parsing   
   English sentences, to find out the grammatical structure of sentences.)   
      
   Torbjorn Lager wrote :   
   > You seem to think that creating a "program with which you can converse   
   in natural language" is simpler than creating a program that can do   
   legal reasoning. As a computational linguist, I believe it is rather   
   the other way around. Since you are a lawyer my advice would be to   
   start with the legal reasoning part.   
   <   
      
   I agree with Torbjorn.  Designing a program that can have a conversation is   
   difficult.   
      
   I recommend that you start by writing a less ambitious program,   
   an Expert System which has legal knowledge.  If you get this working well,   
   you will see the sort of logic that a Prolog program can do, and you will   
   have   
   some idea of the logic that would be needed by a program that can   
   understand English.  You can then decide if you want to take it further,   
   and try to write a program that can understand English.   
      
   I recommend that you start by learning Prolog, then write an Expert System   
   that has some legal knowledge.  I think you can do this in about a year.   
   (I think there is less chance of you getting a program working within four   
   years which can have an unstructured conversation.)   
      
   You can then build up on this program, to give it more legal knowledge, and   
   more complex behaviour.  If you wish, and if you have the time, you can add   
   NLP features to it, so that the user can enter simple sentences which the   
   Expert System responds to.   
      
   Instead of the user having an unstructured conversation with your program,   
   in English, the user is guided through a carefully structured interaction,   
   by the program.  That's what an Expert System does.   
      
   An Expert System finds out what the user wants to know, by asking a series   
   of questions.  It chooses its questions according to answers to previous   
   questions.  Eventually the user has fully specified what he want to know,   
   and the Expert System will then give him an answer.   
      
   Expert Systems are quite well understood by now.  Some books on Prolog   
   give examples of simple Expert Systems, and show how to write one.   
   There are also books on the subject of Expert Systems alone.   
      
   Natural Language Processing is not well understood.  We are still working   
   out how to do it properly.  A single book on Natural Language Processing   
   will normally only cover part of the problem.  You may have to read a number   
   of books, and work through the exercises, before you know what it would take   
   to write a program that can have a conversation.   
      
   --   
   Martin Sondergaard.   
      
      
      
      
   .   
      
   [ comp.ai is moderated.  To submit, just post and be patient, or if ]   
   [ that fails mail your article to , and ]   
   [ ask your news administrator to fix the problems with your system. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)