[b-hebrew] Machine translation of the Bible, was: heno- v's poly- theismin the torah

Read, James C K0434995 at kingston.ac.uk
Fri Jul 29 15:33:23 EDT 2005

Very good observation.
The software is still in phase of architecture. And as you can imagine this is the
most important stage. 
The basic plan to address this issue is this.

a)Construct the base language of translation
b)Develop and test the software with all major living languages especially those
related to Hebrew
c)Match up common phrases in Hebrew with common phrases in living languages by 
means of frequency and usage analysis algorithms

This is, of course an over simplification.
The most important factor is the base language. The major mistake in the past has 
been to use English as the base language. This imposes many Anglicisms on translations
into other languages.
The philosophy behind the mechanisms is that the base language will be concepts and not
words in any modern language. The reason I have decided this is the way forward is 
because of one simple observation: When children learn their first language they relate 
new words to concepts and so a high level of fluency is achieved. When an adult learns 
a second language they start by relating words to other words in their first language, 
which are in turn related to concepts, which is the true basepoint of all languages, 
whether verbal or visual or sensual (i.e. braille). The adult experiences problems with 
communication not because the wrong concepts came to mind but because he has related the 
words of the TL incorrectly to the concepts via the *corrupt* path of words in the FL.
After years of trial and error, the adult may or may not gain flunecy in the TL by eventually 
relating the words of the TL *directly* to the concepts, which are the basepoint of all 
expression and the only language that we all have in common.

I don't know if that was followable. I tried to keep it as simple as possible. Let 
me know if there's something I didn't explain well.

-----Original Message-----
From: b-hebrew-bounces at lists.ibiblio.org on behalf of Heard, Christopher
Sent: Fri 7/29/2005 8:12 PM
To: b-hebrew
Subject: Re: [b-hebrew] Machine translation of the Bible,was:  heno- v's poly- theismin the torah

How does the fact that biblical Hebrew has a very limited corpus and  
can no longer (if it ever could have been) be observed in daily use  
affect the project? Your "childlike" AI will not be able to observe  
real speakers of biblical Hebrew as it could, for example, observe  
real use of modern Japanese or French. It seems to me that even if  
your AI engine is solid and all your language acquisition models are  
spot-on, these pragmatic limitations will hamper the program's  
learning ability. How have you addressed these issues?



On Jul 29, 2005, at 11:42 AM, Read, James C wrote:

> The major reason for their failings is the presupposition that our
> division and definition of words is correct. Current translating
> programs are largely literally based and for this reason they produce
> such poor translations.
> I agree that the project is complex but I have full faith in its  
> possibility.
> The very fact that children can learn a language without having to  
> depend on
> translations shows that the algorithms exist and the program will  
> just as much
> a pyscholgical one as a linguistic one.
> The secret is in finding the algorithms which I believe lie more  
> the minds of
> children than in the prowess of 'scholars'.
> -----Original Message-----
> From: Peter Kirk [mailto:peterkirk at qaya.org]
> Sent: Fri 7/29/2005 5:54 PM
> To: Read, James C
> Cc: b-hebrew at lists.ibiblio.org
> Subject: Machine translation of the Bible, was: [b-hebrew] heno-  
> v's poly- theismin the torah
> On 29/07/2005 16:39, Read, James C wrote:
>> ...
>> In fact, I firmly believe that grammar is more of a hindrance
>> than a help to learning a language and I intend to demonstrate
>> this with my AI project.
>> The purpose of my project is to develop algorithms which analyse
>> any input of language. The alphabet it will use will be based
>> on phonemes and not the inadequate arrays of alphabets that
>> modern languages use.
>> The algorithms will completely avoid grammar and rely entirely
>> on examples and contexts to learn the meanings of words (a word
>> is a series of sounds/phonemes and may not necessarily agree with
>> the classical division of words we are accustomed to).
>> It is my aim that this tool will produce a translation of the
>> hebrew bible, which is completely devoid of doctrinal influences,
>> as a demonstration that the natural way of learning languages
>> is the superior one. It's a big project and the algorithms have
>> many challenges but I am benefitting from the thoughts posted
>> in the various threads.
> James, I wish your project well, but I am not very hopeful for you.
> After all, researchers have been working on machine translation  
> between
> major world languages for many decades, and the best results that they
> can come up with are appalling. For example, a few years ago I used
> Babelfish to translate Psalm 23:1 from English to Chinese to  
> English and
> from German to English, and in both cases got the result "The Lord is
> not my shepherd"! (The "not" was wrongly transferred from the second
> clause.) And even when used on actual web pages the results were
> frequently incomprehensible.
> To come up with a useable Bible translation from Hebrew you will  
> have to
> do very much better than such programs can do even from German. And  
> yet
> the only way you can do this in a way which "is completely devoid of
> doctrinal influences" (a laudable aim, although I don't think an
> achievable one) is to avoid "teaching" the program with ANY
> human-generated translations of Bible passages. But then, as I
> understand it (although I am not at all an expert), the only way that
> the current generation of machine translators can make any real  
> progress
> is by matching to patterns found in real examples of human-generated
> translation. So you will need to find a new approach here.
> Sorry to be discouraging. I fear that your aim is unattainable. But I
> hope that it is not.
> -- 
> Peter Kirk
> peter at qaya.org (personal)
> peterkirk at qaya.org (work)
> http://www.qaya.org/
> -- 
> No virus found in this outgoing message.
> Checked by AVG Anti-Virus.
> Version: 7.0.338 / Virus Database: 267.9.6/59 - Release Date:  
> 27/07/2005
> This email has been scanned for all viruses by the MessageLabs Email
> Security System.
> This email has been scanned for all viruses by the MessageLabs Email
> Security System.
> _______________________________________________
> b-hebrew mailing list
> b-hebrew at lists.ibiblio.org
> http://lists.ibiblio.org/mailman/listinfo/b-hebrew

R. Christopher Heard
Assistant Professor of Religion
Pepperdine University
Malibu, California 90263-4352
b-hebrew mailing list
b-hebrew at lists.ibiblio.org

This email has been scanned for all viruses by the MessageLabs Email
Security System.

This email has been scanned for all viruses by the MessageLabs Email
Security System.

More information about the b-hebrew mailing list