def main():
references = []
sys.stderr.write("Reading English Sentences\n")
for i, line in enumerate(open(opts.en)):
'''Initialize references to correct english sentences'''
references.append(line)
if i%100 == 0:
sys.stderr.write(".")
sys.stderr.write("\nTry reading nbests datastructure from disk ... \n")
nbests = read_ds_from_file(opts.nbestDS)
if nbests is None:
nbests = []
sys.stderr.write("No nbests on disk, so calculating ndests ... \n")
for j,line in enumerate(open(opts.nbest)):
(i, sentence, features) = line.strip().split("|||")
i = int(i)
stats = list(bleu.bleu_stats(sentence, references[i]))
# bleu_score = bleu.bleu(stats)
smoothed_bleu_score = bleu.smoothed_bleu(stats)
# making the feature string to float list
feature_list = [float(x) for x in features.split()]
if len(nbests)<=i:
nbests.append([])
# nbests[i].append(entry(sentence, bleu_score, smoothed_bleu_score, feature_list))
nbests[i].append(entry(sentence, smoothed_bleu_score, feature_list))
if j%5000 == 0:
sys.stderr.write(".")
write_ds_to_file(nbests, opts.nbestDS)
arg_num = len(nbests[0][0].feature_list)
theta = [1.0/arg_num for _ in xrange(arg_num)] #initialization
avg_theta = [ 0.0 for _ in xrange(arg_num)]
avg_cnt = 0
sys.stderr.write("\nTraining...\n")
for j in xrange(opts.epo):
mistake = 0;
for nbest in nbests:
sample = get_sample(nbest)
sample.sort(key=lambda i: i[0].smoothed_bleu - i[1].smoothed_bleu, reverse=True)
for i in xrange(min(len(sample), opts.xi)):
v1 = sample[i][0].feature_list
v2 = sample[i][1].feature_list
if dot_product(theta, v1) <= dot_product(theta, v2):
mistake += 1
theta = vector_plus(theta, vector_plus(v1, v2, -1), opts.eta)
avg_theta = vector_plus(avg_theta, theta)
avg_cnt += 1
sys.stderr.write("Mistake: %s\n" % (mistake,))
weights = [ avg / avg_cnt if avg_cnt !=0 else 1/float(arg_num) for avg in avg_theta ]
sys.stderr.write("Computing best BLEU score and outputing...\n")
# instead of print the averaged-out weights, print the weights that maximize the BLEU score
print "\n".join([str(weight) for weight in weights])
def main():
references = []
sys.stderr.write("Reading English Sentences\n")
for i, line in enumerate(open(opts.en)):
'''Initialize references to correct english sentences'''
references.append(line)
if i % 100 == 0:
sys.stderr.write(".")
sys.stderr.write("\nTry reading nbests datastructure from disk ... \n")
nbests = read_ds_from_file(opts.nbestDS)
if nbests is None:
nbests = []
sys.stderr.write("No nbests on disk, so calculating ndests ... \n")
for j, line in enumerate(open(opts.nbest)):
(i, sentence, features) = line.strip().split("|||")
i = int(i)
stats = list(bleu.bleu_stats(sentence, references[i]))
# bleu_score = bleu.bleu(stats)
smoothed_bleu_score = bleu.smoothed_bleu(stats)
# making the feature string to float list
feature_list = [float(x) for x in features.split()]
if len(nbests) <= i:
nbests.append([])
# nbests[i].append(entry(sentence, bleu_score, smoothed_bleu_score, feature_list))
nbests[i].append(entry(sentence, smoothed_bleu_score,
feature_list))
if j % 5000 == 0:
sys.stderr.write(".")
write_ds_to_file(nbests, opts.nbestDS)
arg_num = len(nbests[0][0].feature_list)
theta = [1.0 / arg_num for _ in xrange(arg_num)] #initialization
avg_theta = [0.0 for _ in xrange(arg_num)]
avg_cnt = 0
sys.stderr.write("\nTraining...\n")
for j in xrange(opts.epo):
mistake = 0
for nbest in nbests:
sample = get_sample(nbest)
sample.sort(key=lambda i: i[0].smoothed_bleu - i[1].smoothed_bleu,
reverse=True)
for i in xrange(min(len(sample), opts.xi)):
v1 = sample[i][0].feature_list
v2 = sample[i][1].feature_list
if dot_product(theta, v1) <= dot_product(theta, v2):
mistake += 1
theta = vector_plus(theta, vector_plus(v1, v2, -1),
opts.eta)
avg_theta = vector_plus(avg_theta, theta)
avg_cnt += 1
sys.stderr.write("Mistake: %s\n" % (mistake, ))
weights = [
avg / avg_cnt if avg_cnt != 0 else 1 / float(arg_num)
for avg in avg_theta
]
sys.stderr.write("Computing best BLEU score and outputing...\n")
# instead of print the averaged-out weights, print the weights that maximize the BLEU score
print "\n".join([str(weight) for weight in weights])
def main():
references = []
sys.stderr.write("Reading English Sentences\n")
for i, line in enumerate(open(opts.en)):
'''Initialize references to correct english sentences'''
references.append(line)
if i%100 == 0:
sys.stderr.write(".")
sys.stderr.write("\nTry reading %s from disk ... \n" % opts.nbestDS)
nbests = read_ds_from_file(opts.nbestDS)
if nbests is None:
nbests = []
sys.stderr.write("%s is not on disk, so calculating it ... \n" % opts.nbestDS)
for j,line in enumerate(open(opts.nbest)):
(i, sentence, features) = line.strip().split("|||")
i = int(i)
stats = list(bleu.bleu_stats(sentence, references[i]))
# bleu_score = bleu.bleu(stats)
smoothed_bleu_score = bleu.smoothed_bleu(stats)
# making the feature string to float list
feature_list = [float(x) for x in features.split()]
if len(nbests)<=i:
nbests.append([])
# nbests[i].append(entry(sentence, bleu_score, smoothed_bleu_score, feature_list))
nbests[i].append(entry(sentence, smoothed_bleu_score, feature_list))
if j%5000 == 0:
sys.stderr.write(".")
sys.stderr.write("\nWriting %s to disk ... \n" % opts.nbestDS)
write_ds_to_file(nbests, opts.nbestDS)
sys.stderr.write("Finish writing %s\n" % opts.nbestDS)
arg_num = len(nbests[0][0].feature_list)
theta = [1.0/arg_num for _ in xrange(arg_num)] #initialization
# avg_theta = [ 0.0 for _ in xrange(arg_num)]
# avg_cnt = 0
tau = opts.tau # positive learning margin
sys.stderr.write("\nTraining...\n")
for iter_num in xrange(opts.epo):
sys.stderr.write("\nIteration#{} ".format(iter_num + 1))
cnt = 0;
# sentence wise updating
for i, nbest in enumerate(nbests):
y = sorted(nbest, key = lambda h: h.smoothed_bleu, reverse = True)
mu = [0.0]*len(nbest)
w_times_x = [0.0]*len(nbest)
for j, best in enumerate(nbest):
# calculate linear function result
w_times_x[j] = dot_product(theta, best.feature_list)
# processing pairs
top_r = int(len(y)*opts.r)
bottom_k = int(len(y)*opts.k)
for j in xrange(len(nbest) - 1):
for l in xrange(j+1, len(nbest)):
if nbest[j].smoothed_bleu <= y[top_r].smoothed_bleu \
and nbest[l].smoothed_bleu >= y[- bottom_k].smoothed_bleu \
and w_times_x[j] > w_times_x[l] + tau:
mu[j] = mu[j] + 1
mu[l] = mu[l] - 1
elif nbest[j].smoothed_bleu >= y[- bottom_k].smoothed_bleu \
and nbest[l].smoothed_bleu <= y[top_r].smoothed_bleu \
and w_times_x[j] > w_times_x[l] - tau:
mu[j] = mu[j] - 1
mu[l] = mu[l] + 1
else:
cnt += 1
if (j + 1) % 100 == 0:
sys.stderr.write(".")
vector_sum = [0 for _ in xrange(len(nbest[0].feature_list))]
for m, best in enumerate(nbest):
vector_sum = vector_plus(vector_sum, scale_product(mu[m], best.feature_list))
theta = vector_plus(theta, vector_sum, opts.eta)
# avg_theta = vector_plus(avg_theta, theta)
# avg_cnt += 1
sys.stderr.write("\n Non-supported vectors: %s\n" % (cnt,))
# weights = [ avg / avg_cnt if avg_cnt !=0 else 1/float(arg_num) for avg in avg_theta ]
sys.stderr.write("Computing best BLEU score and outputing...\n")
# instead of print the averaged-out weights, print the weights that maximize the BLEU score
print "\n".join([str(weight) for weight in theta])
def main():
references = []
sys.stderr.write("Reading English Sentences\n")
for i, line in enumerate(open(opts.en)):
'''Initialize references to correct english sentences'''
references.append(line)
if i % 100 == 0:
sys.stderr.write(".")
sys.stderr.write("\nTry reading %s from disk ... \n" % opts.nbestDS)
nbests = read_ds_from_file(opts.nbestDS)
if nbests is None:
nbests = []
sys.stderr.write("%s is not on disk, so calculating it ... \n" %
opts.nbestDS)
for j, line in enumerate(open(opts.nbest)):
(i, sentence, features) = line.strip().split("|||")
i = int(i)
stats = list(bleu.bleu_stats(sentence, references[i]))
# bleu_score = bleu.bleu(stats)
smoothed_bleu_score = bleu.smoothed_bleu(stats)
# making the feature string to float list
feature_list = [float(x) for x in features.split()]
if len(nbests) <= i:
nbests.append([])
# nbests[i].append(entry(sentence, bleu_score, smoothed_bleu_score, feature_list))
nbests[i].append(entry(sentence, smoothed_bleu_score,
feature_list))
if j % 5000 == 0:
sys.stderr.write(".")
sys.stderr.write("\nWriting %s to disk ... \n" % opts.nbestDS)
write_ds_to_file(nbests, opts.nbestDS)
sys.stderr.write("Finish writing %s\n" % opts.nbestDS)
arg_num = len(nbests[0][0].feature_list)
theta = [1.0 / arg_num for _ in xrange(arg_num)] #initialization
# avg_theta = [ 0.0 for _ in xrange(arg_num)]
# avg_cnt = 0
tau = opts.tau # positive learning margin
sys.stderr.write("\nTraining...\n")
for iter_num in xrange(opts.epo):
sys.stderr.write("\nIteration#{} ".format(iter_num + 1))
cnt = 0
# sentence wise updating
for i, nbest in enumerate(nbests):
y = sorted(nbest, key=lambda h: h.smoothed_bleu, reverse=True)
mu = [0.0] * len(nbest)
w_times_x = [0.0] * len(nbest)
for j, best in enumerate(nbest):
# calculate linear function result
w_times_x[j] = dot_product(theta, best.feature_list)
# processing pairs
top_r = int(len(y) * opts.r)
bottom_k = int(len(y) * opts.k)
for j in xrange(len(nbest) - 1):
for l in xrange(j + 1, len(nbest)):
yj = nbest[j].smoothed_bleu
yl = nbest[l].smoothed_bleu
if yj < yl \
and dist(yj, yl) > opts.epsilon \
and w_times_x[j] - w_times_x[l] < g_learn(yj, yl)*tau:
mu[j] = mu[j] + g_learn(yj, yl)
mu[l] = mu[l] - g_learn(yj, yl)
elif yj > yl \
and dist(yj, yl) > opts.epsilon \
and w_times_x[l] - w_times_x[y] < g_learn(yl, yj)*tau:
mu[j] = mu[j] - g_learn(yl, yj)
mu[l] = mu[l] + g_learn(yl, yj)
else:
cnt += 1
if (j + 1) % 10000 == 0:
sys.stderr.write(".")
vector_sum = [0 for _ in xrange(len(nbest[0].feature_list))]
for m, best in enumerate(nbest):
vector_sum = vector_plus(
vector_sum, scale_product(mu[m], best.feature_list))
theta = vector_plus(theta, vector_sum, opts.eta)
# avg_theta = vector_plus(avg_theta, theta)
# avg_cnt += 1
sys.stderr.write("\n Non-supported vectors: %s\n" % (cnt, ))
# weights = [ avg / avg_cnt if avg_cnt !=0 else 1/float(arg_num) for avg in avg_theta ]
sys.stderr.write("Computing best BLEU score and outputing...\n")
# instead of print the averaged-out weights, print the weights that maximize the BLEU score
print "\n".join([str(weight) for weight in theta])
