From a.rosta@v21.me.uk Thu Jan 06 09:40:08 2005 Return-Path: X-Sender: a.rosta@v21.me.uk X-Apparently-To: lojban@yahoogroups.com Received: (qmail 17210 invoked from network); 6 Jan 2005 17:40:07 -0000 Received: from unknown (66.218.66.217) by m16.grp.scd.yahoo.com with QMQP; 6 Jan 2005 17:40:07 -0000 Received: from unknown (HELO heineken.flexi-surf.co.uk) (62.41.128.20) by mta2.grp.scd.yahoo.com with SMTP; 6 Jan 2005 17:40:06 -0000 Received: from oemcomputer ([217.140.37.133]) by heineken.flexi-surf.co.uk (8.11.6/8.11.6) with SMTP id j06Fekf23782 for ; Thu, 6 Jan 2005 15:40:46 GMT Message-ID: <001701c4f416$b89ef6e0$42e1fea9@oemcomputer> To: References: <20050106062133.GB19161@mit.edu> Date: Thu, 6 Jan 2005 17:33:22 -0000 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1437 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1441 X-eGroups-Remote-IP: 62.41.128.20 From: "And Rosta" Subject: Re: [lojban] Re: some thoughts about lojban use and future X-Yahoo-Group-Post: member; u=175222075 X-Yahoo-Profile: andjamin X-Yahoo-Message-Num: 23575 Rob: > Here are the things we can't do outside of demos: > 1. We can't translate between vastly different languages (like English and > Korean) with any success at all. > 2. We can't parse arbitrary sentences. > 3. Even if we have parse trees, we can't turn them into accurate semantic > representations. > 4. Even if we have accurate semantic representations, we can't put them > together and hold a natural discourse. > > I'm working on a project to use Lojban to get a foot in the door on 2, > 3, and 4. The problem is convincing a professor that artificial language > processing will help natural language processing, but it's not because > the things I'm doing in Lojban have already been accomplished with > natural languages. It's because it seems that we won't accomplish these > things in natural languages for another 15 to 50 years, and most people > have given up on them. For natlangs, 2 & 3 are the fault of linguistics -- it's really hard for the linguist to work out the grammar of a language, but to the extent that linguists succeed with 2 & 3, the computational problem of 2 & 3 -- aside from disambiguation -- ought surely to then be very straightforward. A suitable invented language should make 2 & 3 easy, & make disambiguation unnecessary. But 1 & 4 surely require general intelligence, & the problem is not really a linguistic one: I have no idea how long it will be until computers have general intelligence. --And.