Best turnkey relationship detection library?

Question

What is the best turnkey relationship detection library (ready-to-use, industrial strength)?

I played with NLTK, and the results I get are not very satisfactory.

• http://nltk.googlecode.com/svn/trunk/doc/book/ch07.html
• http://nltk.googlecode.com/svn/trunk/doc/howto/relextract.html

Ideally, I need a library that can accept sentences like:

"Sarah killed the wolf who ate the baby"

and turn it into a data structure that means something like:

killed (Sarah, wolf) And there is (wolf, child)

I know that this is the subject of a large amount of research and that it is not an easy task. However, does anyone know of a reliable enough ready-to-use library for detecting relationships?

Answer 1

Update: Extractiv is no longer available.

Extractiv On-Demand REST service provision: fooobar.com/questions/1786322 / ... will process this page, extract and display the two semantic triples that you want in the lower left corner under the "GENERIC" section. (It removes part of the text from the page in the html viewer, but this text is not discarded if you use json or rdf output).

, , , . -, Language Computer Corporation.

Answer 2

. , Stanford Parser , -- , :

nsubj(killed-2, Sarah-1)
dobj(killed-2, wolf-4)

nsubj(eating-7, wolf-4)
dobj(eating-7, child-9)