def make_scores_lstm(my_rnn, query, answers, emb_size=768, hidden_size=64):
query_embs = bc.encode((clean_punct(cleanhtml(query))).split())
tensor_query_embs = torch.tensor(query_embs)
all_query_hidden, (last_query_hidden, last_query_state) = my_rnn(
tensor_query_embs.unsqueeze(0))
print("all_query_hidden")
#last_answers_hidden = [my_rnn(torch.tensor(bc.encode((clean_punct(cleanhtml(answer))).split())).unsqueeze(0))[1] for answer in answers]
last_answers_hidden = []
for ind, answer in enumerate(answers):
print(ind)
last_answers_hidden.append(
my_rnn(create_tensor(answer).unsqueeze(0))[1][0])
aa = last_query_hidden.detach().numpy()
print("last_answers_hidden")
bb = last_answers_hidden[0].detach().numpy()
#print ("bb shape", bb.shape)
scores = [
cosine_similarity(
last_query_hidden.squeeze(0).detach().numpy(),
last_answer_hidden.squeeze(0).detach().numpy())[0][0]
for last_answer_hidden in last_answers_hidden
]
return scores
def make_scores_cam(query, titles, answers):
print ("make_scores_cam")
query = (cleanhtml(query))
answers_clean = [(cleanhtml(answer)) for answer in answers]
titles_clean = [(cleanhtml(title)) for title in titles]
obj1, obj2, pred, asp = extract_objs_asp(extr, query)
print ("obj1, obj2, pred, asp", obj1, obj2, pred, asp, "\n")
number_of_comparative_sentences = []
for ind, answer in enumerate(answers_clean):
sentenсes = [titles[ind]] + nltk.tokenize.sent_tokenize(answer)
dframe = prepare_sentence_DF(sentenсes, obj1, obj2)
answ = classify_sentences(dframe, 'infersent')
filt = (answ["BETTER"] >= 0.2) | (answ["WORSE"] >= 0.2)
new_answ_df = answ.where(filt)
new_answ_df = new_answ_df.dropna()
number_of_comparative_sentences.append(len(new_answ_df))
return number_of_comparative_sentences
def make_scores_obj(query, answers):
(obj1, obj2, pred, asp) = extract_objs_asp(extr, query)
print("in make scores", obj1, obj2, pred, asp)
scores_answers = [
count_score(cleanhtml(answer), (obj1, obj2, pred, asp))
for answer in answers
]
return scores_answers
def make_scores_1(query, answer_titles):
query_emb = bc.encode([query])
scores = [
cosine_similarity(query_emb.reshape(1, -1),
bc.encode([cleanhtml(answer_title)
]).reshape(1, -1))[0][0]
for answer_title in answer_titles
]
return scores
def create_tensor(strng):
#print ((clean_punct(cleanhtml(strng))).split())
arr = bc.encode((clean_punct(cleanhtml(strng))).split())
return torch.tensor(np.copy(arr))