[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: AI Project
John Cowan stood up, stood up some more, and spoke thus:
>> Is there anything Lojbanic and AI-related that you would recommend I attack?
>Surely you jest, doi pendo be mi. The Obvious Thing is the long-desired
>postprocessor to the Lojban parser that spits out Prolog. That would put
>a new spin on the "navigations" of the ckafybarja; by processing a description
>into a set of Horn clauses, it would be possible to ask questions in Lojban
>about the coffee bar and eventually get more or less sensible answers!
>(True top-end processing would have to go both ways under the control of
>a few pipes.)
>And wouldn't >that< be one up the nose for Schank and all his ilk!
Don't get me involved in *that* one! :)
Just had words with the AI lecturer, and he was quite happy to have me do this;
in his mind, it's excellent paedagogy. Let me clarify for Lojbab: I have
already studied AI as an undergrad, and AI is a compulsory subject in the
CogSci program, but the project I am doing instead of coursework is an AI
project, not a CogSci project.
The problem I have now is: how do I shoehorn this project, which could go
on forever (especially with tanru) into something I can spend at most 80
hours on (and I'd prefer 60)? We will need to decide what domains of the
language we'll have to leave out: this will need to work on a subset of
the language. And I'm sorry to get pushy at this dictionary-producing time,
but I'd like some ideas from you soon: I want to put a proposal on Prof.
Caelli's desk by the end of the week. (It's already second week of the
thirteen-week semester). Of course, I could continue work on the project
after this semester, though the net.love-of-my-life coming over for a visit
in July may slow things down :)
Momenton senpretende paseman mi retenis kaj # [Victor Sadler, _Memkritiko_ 90]
kultis kvazaux & (NICK NICHOLAS. Melbourne.
senhorlogxan elizeon # Australia. IRC: nicxjo.
(Dume: & nsn@munagin.ee.mu.oz.au .)