[Home] [Groups] - Message: [Prev in Group] [Next in Group]

nu.kanga.list.mud-dev

10392: Re: [MUD-Dev] Parsing Text Output

[Full Header] [Plain Text]
From: "Jon A. Lambert" <jlsysinc@ix.netcom.com>
Newsgroups: nu.kanga.list.mud-dev
Date: Fri, 4 Jun 1999 16:14:00 -5
References: [1]
Organization: Kanga.Nu
On 3 Jun 99,, Nathan F Yospe wrote:
> 
> Am I the only one here who uses a NLP for *output*? This is a legitimate
> use of a parser, and as far as I know, I'm the only one attempting quite
> so ambitious an undertaking. Others have mentioned markups and inserting
> weather or time affected variances, as well as attention and focus based
> organization of clips, but ... who else has actually started this? There
> are several things I'd like to hash out with someone...
> 

Quite possibly.  At least I haven't seen anyone post anything remotely
resembling the descriptive logs you have posted in the past.  Now I would 
certainly _like_ to do something similar.  I think that a markup language 
is a good first step.  You _do_ use a markup language, no? 

And as I recall, your output had a nice flow which seemed to smooth out 
all the rough edges that one might expect.  Absent NLP, I would expect to 
see short stilted sentences, the absence of clauses, inconsistencies in 
sentence construction, and wild variations in reader viewpoint between 
sentences.  

I'm interested in how you handle this from the builder side.  What sort 
of effort, practice, experience, tools does a builder need to make your 
system work?  Assume the builder is a marginally competent writer with a 
fair shot at successfully using a word processor.  Could a R.E. Howard, 
for instance, be _effective_ in building on your system?  :)
Also, does your system do anything that would cause multiple authors 
works to be merged?  For instance, have you had one author pen some 
global weather descriptions and another author design a lunar colony?
Are there problems in consistency parsing together multi-authored text?

I suppose I may be using a form NLP in another area, that hasn't yet
been mentioned in these current threads.  I have several 'bots that 
attempt to parse conversation.  My Socrates, for example, is just an 
Eliza clone with his own database.  And I have future plans for a number 
of other 'bots based on different databases and other available AI code.
I plan to implement a 'bot that acts as a guest tour guide.
Anyone have thoughts on this area of NLP?
  

--
--*     Jon A. Lambert - TychoMUD Email:jlsysinc@ix.netcom.com             *--
--*     Mud Server Developer's Page <http://pw1.netcom.com/~jlsysinc>      *--
--* To fight the empire is to be infected by its derangement. Whosoever    *--
--* defeats part of the empire becomes the empire; it proliferates like a  *--
--* a virus... thereby it becomes its enemies." -- P.K. Dick               *--


_______________________________________________
MUD-Dev maillist  -  MUD-Dev@kanga.nu
http://www.kanga.nu/lists/listinfo/mud-dev