def _summarize(self, string, mode, postprocess, **kwargs):
summary = upperfirst(
self._predict(f'{mode}: {summarization_textcleaning(string)}')
)
if postprocess and mode != 'tajuk':
summary = postprocess_summary(string, summary, **kwargs)
return summary
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 _summarize(self, strings, mode, postprocess, **kwargs):
summaries = self._predict([
f'ringkasan: {summarization_textcleaning(string)}'
for string in strings
])
if postprocess and mode != 'tajuk':
summaries = [
postprocess_summary(strings[no], summary, **kwargs)
for no, summary in enumerate(summaries)
]
return summaries
def _summarize(
self,
strings,
mode,
decoder='greedy',
top_p=0.7,
postprocess=True,
**kwargs,
):
mode = mode.lower()
if mode not in ['ringkasan', 'tajuk']:
raise ValueError('mode only supports [`ringkasan`, `tajuk`]')
if not 0 < top_p < 1:
raise ValueError('top_p must be bigger than 0 and less than 1')
decoder = decoder.lower()
if decoder not in ['greedy', 'beam', 'nucleus']:
raise ValueError(
'mode only supports [`greedy`, `beam`, `nucleus`]')
strings_ = [
f'{mode}: {summarization_textcleaning(string)}'
for string in strings
]
batch_x = [self._tokenizer.encode(string) + [1] for string in strings_]
batch_x = padding_sequence(batch_x)
r = self._execute(
inputs=[batch_x, top_p],
input_labels=['Placeholder', 'Placeholder_2'],
output_labels=[decoder],
)
p = r[decoder].tolist()
results = []
for no, r in enumerate(p):
summary = self._tokenizer.decode(r)
if postprocess and mode != 'tajuk':
summary = postprocess_summary(strings[no], summary, **kwargs)
results.append(summary)
return results