IEPY released and demo available

Introducing Iepy an Information Extraction tool

Posted by Elías Andrawos 2 years, 7 months ago Comments
We're happy to announce that IEPY 0.9.3 was released!!
It's an open source tool for Information Extraction focused on Relation Extraction.
It’s aimed at:
  • users needing to perform Information Extraction on a large dataset.
  • scientists wanting to experiment with new IE algorithms.

To give an example of Relation Extraction, if we are trying to find a birth date in:

“John von Neumann (December 28, 1903 – February 8, 1957) was a Hungarian and American pure and applied mathematician, physicist, inventor and polymath.”

Then IEPY’s task is to identify “John von Neumann” and “December 28, 1903” as the subject and object entities of the “was born in” relation.

Demo using TechCrunch

We made a demo/case of study on http://iepycrunch.machinalis.com/ and wrote an article to spread it www.machinalis.com/blog/reading-techcrunch/ . If you consider it interesting, any help in spreading (the post, the demo or the project) would be really appreciated.

Release notes 0.9.3

  • Added grammatical parsing to the preprocess flow of documents
  • Added support for Spanish preprocess
  • Restricted each iepy-instance to a single language
  • Gazetter support
  • Labeling UI improvements
  • Performance and memory usage improvements
  • Model simplifications (labels, metadata)
  • Storage & view of predictions
Documentation: http://iepy.readthedocs.org/en/0.9.3/
Github: https://github.com/machinalis/iepy PyPi: https://pypi.python.org/pypi/iepy Twitter:@machinalis Demo: http://iepycrunch.machinalis.com/

Previous / Next posts


Comments