def translate(sentence, translationMatrix, englishDict, frenchDict, uni, bi, tri, slopeParam, sigmaParam):
frSent = sentence.split()
enLen = int(nrand.normal(len(frSent) / slopeParam, sigmaParam))
enSent = []
dp_mat = []
prob = 1
# creating inverse dictionary
inv_eng = {}
for j in englishDict:
inv_eng[englishDict[j]] = j
# creating top indices
#### To be run once for creating the top 10 index list
#'''
index_list = []
for i in range(len(translationMatrix[0])):
tmplist = []
tmpindex = []
for j in range(len(translationMatrix)):
tmplist.append(translationMatrix[j][i])
tmpindex = sorted(range(len(tmplist)), key=lambda k: tmplist[k], reverse=True)
tmplist2 = []
for j in range(20):
tmplist2.append(tmpindex[j])
index_list.append(tmplist2)
pickle.dump(index_list, open("../top20_index_100_dp.list", "wb"))
#''' and 0
####
top_index = pickle.load(open("../top20_index_100_dp.list", "r"))
## Alignment model
mTemp = len(frSent)
lTemp = enLen
alignmentMatrix_curr = alignmentMatrix[hp.alignmentMapping(mTemp, lTemp)][0:lTemp, 0:mTemp]
for i in range(enLen):
ai = np.argmax(alignmentMatrix_curr[i, 0:mTemp]) # int(nrand.uniform(0, len(frSent)))
currFr = frSent[ai]
currFrInd = frenchDict[currFr]
maxProb = 0
maxInd = 0
template_entry = []
if i == 0:
for j in range(len(translationMatrix)):
template_entry.append(
(inv_eng[j], translationMatrix[j][currFrInd] * lang_model_scores(inv_eng[j], "", uni, bi, 1))
)
dp_mat.append(template_entry)
else:
for j in range(len(translationMatrix)):
maxval = 0
for k in range(len(top_index[0])):
currEngInd = top_index[currFrInd][k]
probtemp = translationMatrix[currEngInd][currFrInd] * lang_model_scores(
inv_eng[currEngInd], dp_mat[i - 1][j][0], uni, bi, 2
)
if maxval < probtemp:
maxval = probtemp
maxword = inv_eng[currEngInd]
template_entry.append((maxword, maxval))
dp_mat.append(template_entry)
translated_sent = ""
maxprob = 0
# print(dp_mat)
for i in range(len(translationMatrix)):
tmp_sent = ""
tmp_prob = 1
for j in range(enLen):
tmp_sent = tmp_sent + dp_mat[j][i][0] + " "
tmp_prob = tmp_prob * dp_mat[j][i][1]
if maxprob <= tmp_prob:
maxprob = tmp_prob
translated_sent = tmp_sent
# print('** Max prob :')
# print(maxprob)
return {"translation": translated_sent, "probability": maxprob}
temp += count_matrix[eng_dict[englishWord]][french_dict[frenchWord]]
lambda_norm[eng_dict[englishWord]] = temp
for frenchWord in french_dict:
translation_matrix[eng_dict[englishWord]][french_dict[frenchWord]] = (count_matrix[eng_dict[englishWord]][french_dict[frenchWord]])/temp
# Computing the mu_matrix
mu_matrix = hp.createMuMatrix()
for s in range(len(eng_sent)):
m_temp = len(french_sent[s])
l_temp = len(eng_sent[s])
t_temp = np.array([[translation_matrix[eng_dict[wi]][french_dict[wj]] for wj in french_sent[s]] for wi in eng_sent[s]])
a_temp = alignment_matrix[hp.alignmentMapping(m_temp, l_temp)][0:l_temp,0:m_temp]
denom_temp = np.reshape(t_temp.transpose().dot(a_temp).diagonal(), (1,m_temp)).repeat(l_temp, 0)
c_ijml = (1.0*a_temp*t_temp)/denom_temp
mu_matrix[hp.alignmentMapping(m_temp, l_temp)][0:m_temp] += np.sum(c_ijml, 0)
'''
for j in range(m_temp):
mu_temp = 0
for i in range(l_temp):
mu_temp += hp.c_of_i_given_jmlFE(i, j, m_temp, l_temp, eng_sent[s], french_sent[s], translation_matrix, alignment_matrix, eng_dict, french_dict)
mu_matrix[hp.alignmentMapping(m_temp, l_temp)][j] += mu_temp
''' and 0
# Updating alignment_matrix
