This code is for the paper entitled "Relation extraction from clinical texts using domain invariant convolutional neural network" which have been published in BioNLP at ACL-2016, Berlin, Germany
Dependencies: Python 2.7, Tensorflow, Numpy, nltk, sklearn, geniatagger
Dataset used in this work was partially availble here. For reproducing the results download complete datset from i2b2 challange that required standard Data Use Agreement and process it in the given format.
PS: The code used here is the modified version of code shared by Denny Britz for sentence classification in his blog wildML http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/