Re: ChatGPT Helpful In Translating Tables

[David Szent-Györgyi]

On Thursday, June 22, 2023 at 11:22:20 AM UTC-4 tbp1...@gmail.com wrote:

Even copying selected text out of a pdf file can be unpleasant.  Often 
there will be no newlines, so words may run together when they were 
visually separated by a line break.


Yes, indeed. Part of my day job involves serving as acquisitions editor for 
content for my employer's Web site, and I must pull content from PDFs from 
all over the world, some of them produced by companies whose workers' 
native language is not in Roman letters. Fishing data out of PDFs is more 
of a toothache than a headache! 

-- 
You received this message because you are subscribed to the Google Groups 
"leo-editor" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to leo-editor+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/leo-editor/3a809cb9-01b7-49d2-aa81-480e030339e4n%40googlegroups.com.

Re: ChatGPT Helpful In Translating Tables

[Thomas Passin]

Even copying selected text out of a pdf file can be unpleasant.  Often 
there will be no newlines, so words may run together when they were 
visually separated by a line break.

On Thursday, June 22, 2023 at 8:52:14 AM UTC-4 David Szent-Györgyi wrote:

> On Sunday, June 18, 2023 at 11:06:30 PM UTC-4 tbp1...@gmail.com wrote:
>
> Very thoughtful piece by Jon Udell - Why LLM-assisted table 
> transformation is a big deal 
> 
> .
>
>  
> In my day job, I have to pull useful items out of PDFs  - pictures, text, 
> tables. PDFs often make this difficult - because of password-protected 
> access, and because the information that renders as neatly organized text 
> and tables when printed or displayed in a viewer is not neatly organized - 
> the data in the PDF requires rearrangement. Jon Udell's article mentions 
> this without discussing the specifics of the articles he processes. 
>
> It is true that tools like ChatGPT are trained on text and as such most 
> likely to work on text, but they do not reason about non-text. I would 
> argue that a PDF is non-text, and as such, recreating neatly organized text 
> and tables is error-prone; if we really value the facts in a technical 
> publication, we need to start with suitable source, which probably needs 
> carefully done markup created by experts in the subject matter of the 
> publication. 
>
> I would not trust a complex table produced by ChatGPT, since it is not 
> only not a subject matter expert, it cannot reason as a human being can 
> when making sense of such a document. 
>
> I don't know what to say about the extraordinary domain of software that 
> produces those PDFs. How many of those software applications incorporate 
> features meant to allow exploration of the structure of a document? This 
> sounds to me like the sort of job for which Leo is well-equipped! 
>

-- 
You received this message because you are subscribed to the Google Groups 
"leo-editor" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to leo-editor+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/leo-editor/acc2979a-b113-4cd1-8b52-283a5aa61e63n%40googlegroups.com.

Re: ChatGPT Helpful In Translating Tables

[David Szent-Györgyi]

On Sunday, June 18, 2023 at 11:06:30 PM UTC-4 tbp1...@gmail.com wrote:

Very thoughtful piece by Jon Udell - Why LLM-assisted table transformation 
is a big deal 

.

 
In my day job, I have to pull useful items out of PDFs  - pictures, text, 
tables. PDFs often make this difficult - because of password-protected 
access, and because the information that renders as neatly organized text 
and tables when printed or displayed in a viewer is not neatly organized - 
the data in the PDF requires rearrangement. Jon Udell's article mentions 
this without discussing the specifics of the articles he processes. 

It is true that tools like ChatGPT are trained on text and as such most 
likely to work on text, but they do not reason about non-text. I would 
argue that a PDF is non-text, and as such, recreating neatly organized text 
and tables is error-prone; if we really value the facts in a technical 
publication, we need to start with suitable source, which probably needs 
carefully done markup created by experts in the subject matter of the 
publication. 

I would not trust a complex table produced by ChatGPT, since it is not only 
not a subject matter expert, it cannot reason as a human being can when 
making sense of such a document. 

I don't know what to say about the extraordinary domain of software that 
produces those PDFs. How many of those software applications incorporate 
features meant to allow exploration of the structure of a document? This 
sounds to me like the sort of job for which Leo is well-equipped! 

-- 
You received this message because you are subscribed to the Google Groups 
"leo-editor" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to leo-editor+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/leo-editor/78528da2-3174-4437-af37-2d763dc28bcfn%40googlegroups.com.

ChatGPT Helpful In Translating Tables

[Thomas Passin]

Very thoughtful piece by Jon Udell - Why LLM-assisted table transformation 
is a big deal 

.

-- 
You received this message because you are subscribed to the Google Groups 
"leo-editor" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to leo-editor+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/leo-editor/69524f8e-4d13-4731-8376-34d6a036cfbcn%40googlegroups.com.