On Thu, Dec 20, 2012 at 11:40 PM, Jörn Kottmann <[email protected]> wrote: > No, not really, sorry. The whole coref component needs some work so its as > easy to use as the other > components in OpenNLP. You are very welcome to help us with that.
I will keep that in mind. :) To be honest I have not really look into the Coref code just yet (mainly been working with seg, tok, pos and ner), but sure, I am willing to contribute > Do you have a data set you would like to train it on? I tried to train it on > the muc data but still had some issues > to reach the performance of the old models (the full training code was never > published by the original author > and I just tried to write my own). Current state of the art results are being compared mainly wrt to the conll task 2011 (using ontonotes 4.0) and SemEval task 2010 (multilingual). http://conll.cemantix.org/2011/ http://semeval2.fbk.eu/semeval2.php?location=tasks#T7 Cheers, Rodrigo
