News for hackers. Stuff that matters.

A comment on Yanukovych leaks. Parent comment

Re:Yanukovych leaks by donohoe on Thursday February 27, 2014 @10:02AM (#7312505)
You should look at DocumentCloud and see if it would be helpful for hosting and managing the documents you're finding.

http://www.documentcloud.org/home

https://github.com/documentcloud

It might be ideal for your needs. The project uses Tesseract‘s OCR to read documents and OpenCalais to pull data from them, including key people, places, and dates.

[ Parent | on HN ]
Re:Yanukovych leaks by pudo on Thursday February 27, 2014 @10:40AM (#7312715)
The project initially used DocumentCloud, but I guess that's built for scenarios which are a little less horrible than single-page JPEGs coming in via FTP.

Tesseract has been working beautifully, we've got the first 1500 documents sent through it. Unfortunately, we don't know the language of each document (trying to get up some crowdsourcing for that), so each gets sent through three times (eng, rus, ukr). Finally, all versions are indexed in ElasticSearch. If anyone has a neater way of doing this (e.g. a good, Python-based language detector), please shout!

[ Parent | on HN ]
Re:Yanukovych leaks by jdimov on Thursday February 27, 2014 @10:29AM (#7312647)
I doubt Tesseract will do well with handwritten Ukrainian... and I am positive OpenCalais won't detect anything in that language.
[ Parent | on HN ]