def _summarize(
self,
strings,
top_p=0.7,
temperature=1.0,
postprocess=True,
**kwargs,
):
strings_ = [summarization_textcleaning(string) for string in strings]
batch_x = [self._tokenizer.encode(string) + [1] for string in strings_]
batch_x = pad_sequences(batch_x, padding='post')
r = self._execute(
inputs=[batch_x, top_p, temperature],
input_labels=['Placeholder', 'top_p', 'temperature'],
output_labels=['logits'],
)
p = r['logits'].tolist()
results = []
for no, r in enumerate(p):
summary = self._tokenizer.decode(r)
if postprocess:
summary = postprocess_summary(strings[no], summary, **kwargs)
results.append(summary)
return results
def greedy_decoder(self, strings: List[str]):
"""
generate a long text given a isi penting.
Decoder is greedy decoder with beam width size 1, alpha 0.5 .
Parameters
----------
strings: List[str]
Returns
-------
result: str
"""
points = [
f'{no + 1}. {remove_repeat_fullstop(string)}.'
for no, string in enumerate(strings)
]
points = ' '.join(points)
points = f'karangan: {points}'
return upperfirst(self._predict(summarization_textcleaning(points)))
