siddharth-agrawal / Neural-Tensor-Network

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

-> This is an implementation of Neural Tensor Network, as mentioned in the following research paper:
   http://nlp.stanford.edu/~socherr/SocherChenManningNg_NIPS2013.pdf
-> The code has been written in Python using Scipy and Numpy
-> The code is bound by The MIT License (MIT)

Running the code:
-> Download the data files: 'entities.txt', 'relations.txt', 'train.txt', 'wordIndices.p', 'dev.txt'
   and 'test.txt' and the code file 'neuralTensorNetwork.py'
-> Put them in the same folder, and run the program by typing in 'python neuralTensorNetwork.py' in the command line
-> You should get a final output saying, 'Accuracy: 0.813', which signifies an accuracy of 81.3%
-> This code takes about a day to execute on an i5 processor

About


Languages

Language:OpenEdge ABL 99.3%Language:Python 0.7%