Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Table Detection and Extraction Using Deep Learning

nanonets.com

Post reply on HN
Print view View original

31–40 of 49 posts

Re: Table Detection and Extraction Using Deep Learning

#31

Post by ackbar03 »

Pandabob wrote: post #24

I applaud the Nanonet folks for starting a business around AI API's, and it seems clear there's lots of value to unlock with solutions like these. But does anyone have insight how hard is it to be in a space where all the big cloud providers seem to be offering very similar products? Can you survive by focusing on a niche segment? Is the market growing so fast that there's room for multiple companies offering (roughl…

I think it's pretty hard and even the big cloud providers dont necessarily have a perfect solution. It's not a particularly creative idea to come up with I think. I've thought about making something similar as a product but I'm kinda glad I didn't

Re: Table Detection and Extraction Using Deep Learning

#32

Post by lowdose »

There is a lot of data locked up in pdfs but even more so in images.

I would like to have a neural net that can give me the data from a chart in an image. I have a hunch image segmentation NN's are able to do this because the size of the surface has a predictive value in the causal relationship. Artificial data could be created at scale with the Google Sheets api.

Re: Table Detection and Extraction Using Deep Learning

#34

Post by jjohansson »

Disclaimer: I work for PDFTron

This is a very interesting field, and PDFTron has been doing similar work with ML and table extraction as part of our document understanding platform. We've made pretty good progress over the past year -- you can try it on your docs here:

https://www.pdftron.com/pdf-tools/pdf-table-extraction/

We also have a rules-based table extraction product (PDFGenie) that works reasonably well, but ML is most definitely the future.

Re: Table Detection and Extraction Using Deep Learning

#35

Post by jessaustin »

nightcracker wrote: post #23
crispyambulance wrote: post #20

Earlier quoted context omitted.

It was really shocking when I learned that the way pdf works is as you describe, literally fragments of text with positions and essentially no semantics. I think a lot of folks find this out as I did, when they run into a project where they need to extract info from pdf documents. Without knowing anything about pdf, one can easily assume that it will be possible to do things like "can't we just extract some semantic…

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...

Re: Table Detection and Extraction Using Deep Learning

#36

Post by jessaustin »

chriskanan wrote: post #22

With collaborators at Adobe Research, my lab published a paper recently showing how to do table reconstruction from infographics (e.g., bar charts) using deep learning [1]. While it isn't the sexiest project, I've had a number of companies reach out about the project. Human written rule-based approaches are pretty bad at the task, and even humans doing it manually aren't great (likely due to sloppiness). [1] https://…

I've found that when PDFs are produced by a single entity for a particular purpose, I can automate this pretty well with a loop and some regex... maybe I've just gotten lucky?

Re: Table Detection and Extraction Using Deep Learning

#37

Post by crispyambulance »

nightcracker wrote: post #23
crispyambulance wrote: post #20

Earlier quoted context omitted.

It was really shocking when I learned that the way pdf works is as you describe, literally fragments of text with positions and essentially no semantics. I think a lot of folks find this out as I did, when they run into a project where they need to extract info from pdf documents. Without knowing anything about pdf, one can easily assume that it will be possible to do things like "can't we just extract some semantic…

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 around it? In the late 90's many of us thought that all documents would be xml for content and styling would be through xslt or even it's big sister, xsl. Well, THAT went nowhere despite all the W3C meetings and papers.

It's interesting you brought up graphics as an analogy. It's true that you can have graphics which are literally just lines and that's adequate for many needs. However, modern CAD drawing systems increasingly use notions of 2D/3D objects and a disciplined series of transformations. They call it "parametric modeling" and it's where where all drawing consist of a series of transformations that can be represented in a timeline. I suspect modern parametric model CAD can very much be semantic.

Re: Table Detection and Extraction Using Deep Learning

#38

Post by tensor »

willvarfar wrote: post #7

I'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.…

Having worked with OCR products doing table detection for years, simple hand written rules cannot solve the general case. It can work for specific documents, but if you want to be able to handle any document it's just not accurate once you include non-gridded tables.

Re: Table Detection and Extraction Using Deep Learning

#39

Post by tensor »

Animats wrote: post #2

Table extraction has been a feature of better OCR programs for at least a decade. It's easier than the OCR part. Look up "OCR table" for examples, products, code, papers, etc.

Gridded tables is not too hard, but once you remove the grid lines, even a portion of them, it becomes a complete crap shoot.

Re: Table Detection and Extraction Using Deep Learning

#40

Post by tastyminerals »

Animats wrote: post #2

Table extraction has been a feature of better OCR programs for at least a decade. It's easier than the OCR part. Look up "OCR table" for examples, products, code, papers, etc.

It does not work reliably and the quality is not something you can only sell as an addon feature. This is what Abbyy does for example.
Post reply on HN