def run(sentence, tagset, hmm_prob):
max_iterations = 200
#step_size = 100
n = len(sentence)
u = {}#defaultdict() # dual decomposition parameter
init_dd_param(u, n, tagset)
k = 1 # number of iterations
while k <= max_iterations:
step_size = 1.0 / math.sqrt(k)
#print "\niteration:", k
#print "-------------------------------"
#print "step size = ", "{0:.2f}".format(step_size)
tags1, aug_hmm_score, hmm_score = viterbi.run(sentence, tagset, hmm_prob, u)
#print "vit output:", ' '.join(tags1)
if k == 1:
best_tags = tags1
tags2, fst_score = fst_search.run(best_tags, u, tagset)
if agree(tags1, tags2):
#sys.stderr.write("hmm only = "+ str( hmm_score) + "\n")
#sys.stderr.write("fst only = "+ str(fst_score) + "\n")
#sys.stderr.write("big hmm = "+ str(aug_hmm_score) + "\n")
#sys.stderr.write("hmm fst = "+ str(aug_hmm_score + fst_score) + "\n")
return best_tags, k, tags1, tags2 # converges in the kth iteration
y = compute_indicators(tags1, tagset)
z = compute_indicators(tags2, tagset)
update(y, z, u, step_size)
k += 1
return best_tags, -1, tags1, tags2 # does not converge
def run(sentence, tagset, hmm, k_best_list):
max_iter = len(k_best_list)*200
n = len(sentence)
k = len(k_best_list)
u = {} # dual decomposition parameter
init_dd_param(u, n, tagset)
iteration = 1
while iteration <= max_iter:
#print iteration
step_size = 1.0 / math.sqrt(iteration)
#print "step size", step_size
seq1, score1, score2 = viterbi.run(sentence, tagset, hmm, u)
y = compute_indicators(seq1, tagset)
#print 0, ' '.join(seq1)
seq2, fst_score = fst_search.run(k_best_list, u, tagset)
z = compute_indicators(seq2, tagset)
#print j+1, ' '.join(seq)
# check for agreement
if seq1 != seq2:
update(y, z, u, step_size)
else:
return seq1, iteration
iteration += 1
return seq1, -1
def run(sentence, tagset, hmm, k_best_list):
max_iter = len(k_best_list) * 200
n = len(sentence)
k = len(k_best_list)
u = [] # dd parameter list
for j in range(k + 1):
u_j = {}
init_dd_param(u_j, n, tagset)
u.append(u_j)
w = {}
init_dd_param(w, n, tagset)
ku = {}
init_dd_param(ku, n, tagset)
iteration = 1
while iteration <= max_iter:
# print iteration
step_size = 21.0 / math.sqrt(iteration)
# print "step size", step_size
seqs = []
indicators = []
for i in u[0].iterkeys():
for t in u[0][i].iterkeys():
ku[i][t] = -1 * u[0][i][t]
seq1, score1, score2 = viterbi.run(sentence, tagset, hmm, ku)
seqs.append(seq1)
indicators.append(compute_indicators(seq1, tagset))
# print 0, ' '.join(seq1)
for j in range(k):
seq, fst_score = fst_search.run(k_best_list[j], u[j + 1], tagset)
# print j+1, ' '.join(seq)
seqs.append(seq)
indicators.append(compute_indicators(seq, tagset))
# check for agreement
agree = True
for seq in seqs[1:]:
if seq != seq1:
agree = False
break
if agree == False:
update(indicators, u, w, step_size)
else:
return seq1, iteration
iteration += 1
return seq1, -1
