def expectation_check(training_sentences,training_labels,w):
lhs_array = np.zeros(np.size(w))
rhs_array = np.zeros(np.size(w))
for i in range(len(training_labels)):
y = training_labels[i]
x = training_sentences[i]
N = len(y)
x_info = ff.sent_precheck(x)
for k in range(1,N):
trueFF = ff.metaff(y[k-1],y[k],x_info,k)
for j in trueFF:
lhs_array[j] += 1
g = sr.g(w,x)
e_g = np.exp(g)
alpha = sr.alpha_mat(g)
beta = sr.beta_mat(g)
z = sr.Z(alpha,beta)
for k in range(np.shape(g)[0]):
for m1 in range(8):
for m2 in range(8):
factor = alpha[k,m1]*beta[k+1,m2]*e_g[k,m1,m2]/z
#get list of non-zero (and thus =1) f_j for (i,m1,m2)
trueFF = ff.metaff(m1,m2,x_info,k)
#add the weighting factor to them
for j in trueFF:
rhs_array[j] += factor
return lhs_array,rhs_array
def LCL_single(x,y,w):
"""
computes the LCL for a single training example
"""
x_info = ff.sent_precheck(x)
g = sr.g(w,x)
alpha = sr.alpha_mat(g)
beta = sr.beta_mat(g)
z = sr.Z(alpha,beta)
N = len(x)
sum_on_j = 0.0
for i in range(1,N):
trueFF = ff.metaff(y[i-1],y[i],x_info,i)
for j in trueFF:
sum_on_j += w[j]
LCL = -math.log(z)
return LCL
def compute_gradient(x, y, w, dw):
"""
This term computes the gradient vector
"""
dw *= 0.0
# get info about this training example
x_info = ff.sent_precheck(x)
N = len(x)
# compute some necessary arrays of factors from the subroutines module
g = sr.g(w, x)
e_g = np.exp(g)
alpha = sr.alpha_mat(g)
beta = sr.beta_mat(g)
z = sr.Z(alpha, beta)
# iterate over position in sentence and tag values, getting a list of indices
# of feature functions to update at for each position and tag pair value.
for i in range(np.shape(g)[0]):
for m1 in range(8):
for m2 in range(8):
factor = alpha[i, m1] * beta[i + 1, m2] * e_g[i, m1, m2] / z
# get list of non-zero (and thus =1) f_j for (i,m1,m2)
# print m1,m2,x_info,i
trueFF = ff.metaff(m1, m2, x_info, i + 1)
# add the weighting factor to them
for j in trueFF:
dw[j] -= factor
# now I go through and use data from y to compute the "true" value of F_J,
# once more iterating over i, but not m1,m2 (instead getting those values
# from the supplied y
for i in range(1, N):
trueFF = ff.metaff(y[i - 1], y[i], x_info, i)
for j in trueFF:
dw[j] += 1
return dw
