Tried extracting data from a newspaper. It is really hard. What is a headline and which headline belongs to which paragraphs? Harder than you think! And chucking it as is into OpenAI was no good at all. Manually dealing with coordinates from OCR was better but not perfect.
PDF to Text, a challenging problem
111–120 of 206 posts
Re: PDF to Text, a challenging problem
#112Re: PDF to Text, a challenging problem
#113Earlier quoted context omitted.
PDFs inherently are a markup / xml format, the standard is available to learn from. It's possible to create the same PDF in many, many, many ways. Some might lean towards exporting a layout containing text and graphics from a graphics suite. Others might lean towards exporting text and graphics from a word processor, which is words first. The lens of how the creating app deals with information is often something that…
> PDFs inherently are a markup / xml format This is false. PDFs are an object graph containing imperative-style drawing instructions (among many other things). There’s a way to add structural information on top (akin to an HTML document structure), but that’s completely optional and only serves as auxiliary metadata, it’s not at the core of the PDF format.
> but that’s completely optional and only serves as auxiliary metadata, it’s not at the core of the PDF format.
This is what I kind of suspected but, as I said in my original comment, I'm not an expert and for the PDFs I'm reading I didn't need to delve further because that metadata simply isn't in there (although, boy do I wish it was) so I needed to use a different approach. As soon as I realised what I had was purely presentation I knew it was going to be a bit grim.
Re: PDF to Text, a challenging problem
#114Maybe it's time for new document formats and browsers that neatly separate content, presentation and UI layers? PDF and HTML are 20+ years old and it's often difficult to extract information from either let alone author a browser.
Yes, but I'm sure they're out there somewhere ( https://xkcd.com/927/ )
Open XML Paper Specification is an XML-based format intended to compete with PDF. Unlike PDF, it is purely static: no scripting.
Also unlike PDF, I've never seen it actually used in the wild.
Re: PDF to Text, a challenging problem
#115I've been using Azure's "Document Intelligence" thingy (prebuilt "read" model) to extract text from PDFs with pretty good results [1]. Their terminology is so bad, it's easy to dismiss the whole thing for another Microsoft pile, but it actually, like, for real, works.
[1] https://learn.microsoft.com/en-us/azure/ai-services/document...
Re: PDF to Text, a challenging problem
#116I did some contract work some years back with a company who had a desktop product (for Mac) that would apply some smarts to strip out extraneous things on pages while printing (such as ads on webpages) as well as try to avoid the case where only a line or two was printed on a page, wasting paper. It initially was getting into things at the PostScript layer, which unsurprisingly was horrifying, but eventually worked on PDFs. This required finding and interpreting various textual parts of the passed documents and was a pretty big technical challenge.
While I'm not convinced it was viable at the business level, it feels like something platform/OS companies could focus on to have a measurable environmental and cost overhead impact.
Re: PDF to Text, a challenging problem
#117"PDF to Text" is a bit simplified IMO. There's actually a few class of problems within this category: 1. reliable OCR from documents (to index for search, feed into a vector DB, etc) 2. structured data extraction (pull out targeted values) 3. end-to-end document pipelines (e.g. automate mortgage applications) Marginalia needs to solve problem #1 (OCR), which is luckily getting commoditized by the day thanks to models…
>replace their OCR pipelines with Flash for a fraction of the cost of previous solutions, it's really quite remarkable. As someone who had to build custom tools because VLMs are so unreliable: anyone that uses VLMs for unprocessed images is in for more pain than all the providers which let LLMs without guard rails interact directly with consumers. They are very good at image labeling. They are ok at very simple docum…
I wish I could upvote you more. The compounding errors of these document solutions preclude what people assume must be possible.
Re: PDF to Text, a challenging problem
#118Yeah, getting text - even structured text - out of PDFs is no picnic. Scraping a table out of an HTML document is often straightforward even on sites that use the "everything's a " (anti-)pattern, and especially on sites that use more semantically useful elements, like . Not so PDFs. I'm far from an expert on the format, so maybe there is some semantic support in there, but I've seen plenty of PDFs where tables are s…
I am hoping at some point to be able to extract tabular data from PDFs for my data wrangling software. If anyone knows of a library that can extract tables from PDFs, can be inegrated into a C++ app and is free or less than a few hundred $, please let me know!
pdfplumber is great for table extraction but it is python
Re: PDF to Text, a challenging problem
#119"PDF to Text" is a bit simplified IMO. There's actually a few class of problems within this category: 1. reliable OCR from documents (to index for search, feed into a vector DB, etc) 2. structured data extraction (pull out targeted values) 3. end-to-end document pipelines (e.g. automate mortgage applications) Marginalia needs to solve problem #1 (OCR), which is luckily getting commoditized by the day thanks to models…
I've been hacking away at trying to process PDFs into Markdown, having encountered similar obstacles to OP regarding header detection (and many other issues). OCR is fantastic these days but maintaining a global structure to the document is much trickier. Consistent HTML seems still out of reach for large documents. I'm having half-decent results with Markdown using multiple passes of an LLM to extract document struc…
Give this project a try. I've been using it with promising results.
Re: PDF to Text, a challenging problem
#120Earlier quoted context omitted.
> PDFs inherently are a markup / xml format This is false. PDFs are an object graph containing imperative-style drawing instructions (among many other things). There’s a way to add structural information on top (akin to an HTML document structure), but that’s completely optional and only serves as auxiliary metadata, it’s not at the core of the PDF format.
I appreciate the clarification. Should have been more precise with my terminology. That being said, I think I'm talking about the forest of PDFs. When I said PDFs have a "markup-like structure," I was talking from my experience manually writing PDFs from scratch using Adobe's spec. PDFs definitely have a structured, hierarchical format with nested elements that looks a lot like markup languages conceptually. The obje…
Markup is only indirectly related to hierarchical structure. “Markup” means that there is text that is being “marked up” with additional attributes (styling, structure information, metadata, …). This is how HTML and XML work, and also languages like TeX, Troff, and Markdown. For example, in the text “this is some text”, you can mark up the word “some” as being emphasized, as in “this is some text”.
The general principle is that the base content is plain text, which is augmented with markup information, which may or may not have hierarchical aspects. You can simply strip away the markup again and recover just the text. That’s not at all how PDF works, however.
You cite a comparison to JSON and YAML. Those are not markup languages (despite what YAML originally was an abbreviation for, see [0]). (HTML also isn’t DOM.)