def evaluate(self, text, aspect):
aspect = aspect.lower().strip()
text_left, _, text_right = [
s.strip() for s in text.lower().partition(aspect)
]
text_indices = self.tokenizer.text_to_sequence(text_left + " " +
aspect + " " +
text_right)
context_indices = self.tokenizer.text_to_sequence(text_left + " " +
text_right)
left_indices = self.tokenizer.text_to_sequence(text_left)
left_with_aspect_indices = self.tokenizer.text_to_sequence(text_left +
" " +
aspect)
right_indices = self.tokenizer.text_to_sequence(text_right,
reverse=True)
right_with_aspect_indices = self.tokenizer.text_to_sequence(
aspect + " " + text_right, reverse=True)
aspect_indices = self.tokenizer.text_to_sequence(aspect)
left_len = np.sum(left_indices != 0)
aspect_len = np.sum(aspect_indices != 0)
aspect_boundary = np.asarray([left_len, left_len + aspect_len - 1],
dtype=np.int64)
text_len = np.sum(text_indices != 0)
concat_segments_indices = [0] * (text_len + 2) + [1] * (aspect_len + 1)
concat_segments_indices = word_util.pad_and_truncate(
concat_segments_indices, self.tokenizer.max_seq_len)
dependency_graph = dependency_adj_matrix(text)[0]
head_vector, behead_vector, relation_vector = to_relation_word_message(
dependency_graph)
data = {
'concat_segments_indices': concat_segments_indices,
'text_indices': text_indices,
'context_indices': context_indices,
'left_indices': left_indices,
'left_with_aspect_indices': left_with_aspect_indices,
'right_indices': right_indices,
'right_with_aspect_indices': right_with_aspect_indices,
'aspect_indices': aspect_indices,
'aspect_boundary': aspect_boundary,
'dependency_graph': dependency_graph,
'head_vector': head_vector,
'behead_vector': behead_vector,
'relation_vector': relation_vector
}
t_inputs = [
torch.tensor([data[col]], device=self.opt.device)
for col in self.opt.input_controller
]
t_outputs = self.model(t_inputs)
t_probs = F.softmax(t_outputs, dim=-1).cpu().numpy()
return t_probs
def evaluate(self, raw_text):
text_seqs = [self.tokenizer.text_to_sequence(raw_text.lower())]
# aspect_seqs = [self.tokenizer.text_to_sequence(aspect.lower())]
# left_seqs = [self.tokenizer.text_to_sequence(raw_text.lower().split(aspect.lower())[0])]
text_indices = torch.tensor(text_seqs, dtype=torch.int64)
# aspect_indices = torch.tensor(aspect_seqs, dtype=torch.int64)
# left_indices = torch.tensor(left_seqs, dtype=torch.int64)
dependency_graph = torch.tensor(
[dependency_adj_matrix(raw_text.lower())])
data = {
'text_indices': text_indices,
'dependency_graph': dependency_graph
}
t_inputs = [data[col].to(opt.device) for col in self.opt.inputs_cols]
t_outputs = self.model(t_inputs)
t_probs = F.softmax(t_outputs, dim=-1).cpu().numpy()
return t_probs
def evaluate(self, text, aspect):
aspect = aspect.lower().strip()
text_left, _, text_right = [
s.strip() for s in text.lower().partition(aspect)
]
text_indices = self.tokenizer.text_to_sequence(text_left + " " +
aspect + " " +
text_right)
context_indices = self.tokenizer.text_to_sequence(text_left + " " +
text_right)
left_indices = self.tokenizer.text_to_sequence(text_left)
left_with_aspect_indices = self.tokenizer.text_to_sequence(text_left +
" " +
aspect)
right_indices = self.tokenizer.text_to_sequence(text_right,
reverse=True)
right_with_aspect_indices = self.tokenizer.text_to_sequence(
aspect + " " + text_right, reverse=True)
aspect_indices = self.tokenizer.text_to_sequence(aspect)
left_len = np.sum(left_indices != 0)
aspect_len = np.sum(aspect_indices != 0)
aspect_boundary = np.asarray([left_len, left_len + aspect_len - 1],
dtype=np.int64)
text_len = np.sum(text_indices != 0)
concat_bert_indices = self.tokenizer.text_to_sequence('[CLS] ' +
text_left + " " +
aspect + " " +
text_right +
' [SEP] ' +
aspect +
" [SEP]")
concat_segments_indices = [0] * (text_len + 2) + [1] * (aspect_len + 1)
concat_segments_indices = pad_and_truncate(concat_segments_indices,
self.tokenizer.max_seq_len)
text_bert_indices = self.tokenizer.text_to_sequence("[CLS] " +
text_left + " " +
aspect + " " +
text_right +
" [SEP]")
aspect_bert_indices = self.tokenizer.text_to_sequence("[CLS] " +
aspect +
" [SEP]")
dependency_graph = dependency_adj_matrix(text)
data = {
'concat_bert_indices': concat_bert_indices,
'concat_segments_indices': concat_segments_indices,
'text_bert_indices': text_bert_indices,
'aspect_bert_indices': aspect_bert_indices,
'text_indices': text_indices,
'context_indices': context_indices,
'left_indices': left_indices,
'left_with_aspect_indices': left_with_aspect_indices,
'right_indices': right_indices,
'right_with_aspect_indices': right_with_aspect_indices,
'aspect_indices': aspect_indices,
'aspect_boundary': aspect_boundary,
'dependency_graph': dependency_graph,
}
t_inputs = [
torch.tensor([data[col]], device=self.opt.device)
for col in self.opt.inputs_cols
]
t_outputs = self.model(t_inputs)
t_probs = F.softmax(t_outputs, dim=-1).cpu().numpy()
return t_probs