Created
December 10, 2012 04:54
-
-
Save satomacoto/4248449 to your computer and use it in GitHub Desktop.
[He 2012] Document Summarization based on Data Reconstruction
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
import numpy as np | |
class DSDR: | |
"""Z He, et al. Document Summarization based onData Reconstruction (2012) | |
http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/viewPaper/4991 | |
""" | |
@staticmethod | |
def lin(V, m, lamb): | |
'''DSDR with linear reconstruction | |
Parameters | |
========== | |
- V : 2d array_like, the candidate data set | |
- m : int, the number of sentences to be selected | |
- lamb : float, the trade off parameter | |
Returns | |
======= | |
- L : list, the set of m summary sentences indices | |
''' | |
L = [] | |
V = np.array(V) | |
B = np.dot(V, V.T) / lamb | |
n = len(V) | |
for t in range(m): | |
scores = [] | |
for i in range(n): | |
score = np.sum(B[:,i] ** 2) / (1. + B[i,i]) | |
scores += [(score, i)] | |
max_score, max_i = max(scores) | |
L += [max_i] | |
B = B - np.outer(B[:,max_i], B[:,max_i]) / (1. + B[max_i,max_i]) | |
return L | |
@staticmethod | |
def non(V, gamma, eps=1.e-8): | |
'''DSDR with nonnegative linear reconstruction | |
Parameters | |
========== | |
- V : 2d array_like, the candidate sentence set | |
- gamma : float, > 0, the trade off parameter | |
- eps : float, for converge | |
Returns | |
======= | |
- beta : 1d array, the auxiliary variable to control candidate sentences | |
selection | |
''' | |
V = np.array(V) | |
n = len(V) | |
A = np.ones((n,n)) | |
beta = np.zeros(n) | |
VVT = np.dot(V, V.T) # V * V.T | |
np.seterr(all='ignore') | |
while True: | |
_beta = np.copy(beta) | |
beta = (np.sum(A ** 2, axis=0) / gamma) ** .5 | |
while True: | |
_A = np.copy(A) | |
A *= VVT / np.dot(A, VVT + np.diag(beta)) | |
A = np.nan_to_num(A) # nan (zero divide by zero) to zero | |
if np.sum(A - _A) < eps: break | |
if np.sum(beta - _beta) < eps: break | |
return beta | |
if __name__ == '__main__': | |
pass |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
import unittest | |
from dsdr import DSDR | |
class TestDSDR(unittest.TestCase): | |
def test_lin(self): | |
''' | |
>>> DSDR.lin(V, m=2, lamb=0.1) | |
[2, 4] | |
''' | |
V = [[1,0,0,0], | |
[0,1,0,0], | |
[1,1,0,0], | |
[0,0,1,0], | |
[0,0,1,1]] | |
L = DSDR.lin(V, m=2, lamb=0.1) | |
print L | |
# show summary | |
for i in L: | |
print V[i] | |
def test_non(self): | |
''' | |
>>> DSDR.non(V, gamma=0.1) | |
[ 0.49301097 0.49301097 0.6996585 0.49301097 0.70211699] | |
''' | |
V = [[1,0,0,0], | |
[0,1,0,0], | |
[1,1,0,0], | |
[0,0,1,0], | |
[0,0,1,1]] | |
beta = DSDR.non(V, gamma=0.1) | |
print beta | |
# show summary | |
for score, v in sorted(zip(beta, V), reverse=True): | |
print score, v | |
if __name__ == '__main__': | |
unittest.main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thank you...but please how can i pass text to it to make summarize the text for me instead of 0, 1 there