Table detection is useful for line item extraction from financial documents and it is solvable. However, generic table extraction is very difficult.
Table Detection and Extraction Using Deep Learning
41–49 of 49 posts
Re: Table Detection and Extraction Using Deep Learning
#42I've worked with several companies that try to parse things in PDF documents, extracting tables and paragraphs etc. This is actually challenging because a PDF is a large bag of words and fragments of words with x y positions. There is a particularly popular word processor that emits individual characters. Just determining that two fragments are part of the same word is challenging as is detecting bullet points, etc.…
I had to check we hadn't worked for the same company! Yeah, text extraction and layout analysis from PDFs is a super interesting challenge and still relatively underdeveloped. I'd put table detection at about the hardest challenge in that field. One of the contributors to the PDF library I'm developing has been implementing some interesting algorithms for layout analysis https://github.com/UglyToad/PdfPig/wiki/Docume…
It depends. We do commercial pdf and scanned information extraction as well as table detection for line items for invoices, receipts and remittance slips. We have been successfully using rule-based system for years but are mixing in deep learning now. I also know a about 5 other companies competing in the same field. So, I wouldn't say it is underdeveloped.
Re: Table Detection and Extraction Using Deep Learning
#43I can see the use-case and potential for ML in exfiltrating tables, but I'd be worried about the potential for decision-making mistakes in environments the author identifies, such as finance. The example of TableNet using deep learning for table extraction on top of tesseract for OCR means two layers of ML, either of which could individually introduce pathologies without human oversight. It reminds me of the photocop…
yes, that's why in financial domain you use rules with ML as fallback.
Re: Table Detection and Extraction Using Deep Learning
#44I was very impressed with "Camelot" (https://camelot-py.readthedocs.io/en/master/). My impression was that it extracted maybe 80 or 90% of the text properly, far better than anything else I had tried.
Re: Table Detection and Extraction Using Deep Learning
#45I've worked with several companies that try to parse things in PDF documents, extracting tables and paragraphs etc. This is actually challenging because a PDF is a large bag of words and fragments of words with x y positions. There is a particularly popular word processor that emits individual characters. Just determining that two fragments are part of the same word is challenging as is detecting bullet points, etc.…
Do you have recommendations for which libraries or APIs currently perform the best at extracting tables and extracting text?
Scanning the comments I see two mentions of Camelot [1] and one mention each of PDFTron [2] and ExtractTable [3].
[1]: https://camelot-py.readthedocs.io/en/master/
[2]: https://www.pdftron.com/pdf-tools/pdf-table-extraction/
[3]: https://extracttable.com/
Would love to hear if you’ve compared across multiple options.
Re: Table Detection and Extraction Using Deep Learning
#46Earlier quoted context omitted.
It's so successful precisely because it doesn't have semantics. It is a print format with one goal: show the output as desired. Semantics only confuse and limit this goal. Imagine how bogged down and limited vector graphics would be if every element had to have semantic meaning? "This line connects the of the to the 13th on the ".
Yeah, so by eliminating semantic concerns, pdf has achieved transcendence as a document format. But by its nature text is intrinsically semantic. I am just surprised that a document format utterly free of semantics has lasted so long. Perhaps because we (as people and organizations) can't agree on the structure of documents? Another way to see this, perhaps, is as the failure of the promise of xml and the ecosystem a…
Books have about the same amount of semantic information as pdf. It's probably just habit.
I think more than lack of agreement, it's just that there aren't really universal document structures. There's relatively useful chunks like paragraphs that are more or less universal (at least for a given language), but those don't need much structure to be clear.
Re: Table Detection and Extraction Using Deep Learning
#47Earlier quoted context omitted.
It's so successful precisely because it doesn't have semantics. It is a print format with one goal: show the output as desired. Semantics only confuse and limit this goal. Imagine how bogged down and limited vector graphics would be if every element had to have semantic meaning? "This line connects the of the to the 13th on the ".
ISTM semantics could have been added as a supplement to PDF à la microformats for HTML, which wouldn't have hurt anything. It's easy for processors to just skip some well-defined tokens. Of course, few producers of PDFs for public consumption would have incentives to do that, so it probably never would have taken off...
Just look at how popular it is to embed/attach arbitrary files to pdf documents.
(it's well supported by Adobe tools...)
Re: Table Detection and Extraction Using Deep Learning
#48Earlier quoted context omitted.
Yeah, so by eliminating semantic concerns, pdf has achieved transcendence as a document format. But by its nature text is intrinsically semantic. I am just surprised that a document format utterly free of semantics has lasted so long. Perhaps because we (as people and organizations) can't agree on the structure of documents? Another way to see this, perhaps, is as the failure of the promise of xml and the ecosystem a…
Books have about the same amount of semantic information as pdf. It's probably just habit. I think more than lack of agreement, it's just that there aren't really universal document structures. There's relatively useful chunks like paragraphs that are more or less universal (at least for a given language), but those don't need much structure to be clear.
It isn’t in the interests of word processors to round-trip through pdf. If you look at the PDFs the mainstream word processors generate, you see some of them actively trying to stop text extraction. It’s like an obfuscation arms race. They include white-on-white text, and jump all over the page positioning text so no whole words occur in the source etc. Sad but true.
Re: Table Detection and Extraction Using Deep Learning
#49Also in the extracting-structured-data-from-PDFs solution space, there is Parsr which was recently posted on HN: https://github.com/axa-group/Parsr see https://news.ycombinator.com/item?id=22035258
It's based on a pipeline of various js modules and pluggable backends (e.g. tesseract, GCP cloud vision, Abbyy API, etc.)
For tables with numbers in them, it worked pretty well, but I'm yet to find a tool that can parse/understand documents where the entire page is a table layout with lots of merged cells. I think even for humans it's hard to understand the structure in those cases...