def _summarize(self, string, mode, postprocess, **kwargs):
summary = upperfirst(self._predict(f'{mode}: {cleaning(string)}'))
if postprocess:
summary = filter_rouge(string, summary, **kwargs)
summary = postprocessing_summarization(summary)
summary = find_lapor_and_remove(string, summary)
return summary
def _summarize(
self,
strings,
mode,
top_p=0.7,
temperature=1.0,
postprocess=True,
**kwargs,
):
mode = mode.lower()
if mode not in ['ringkasan', 'tajuk']:
raise ValueError('mode only supports [`ringkasan`, `tajuk`]')
strings_ = [f'{mode}: {cleaning(string)}' for string in strings]
batch_x = [self._tokenizer.encode(string) + [1] for string in strings_]
batch_x = pad_sequences(batch_x, padding='post', maxlen=self._maxlen)
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 and mode != 'tajuk':
summary = filter_rouge(strings[no], summary, **kwargs)
summary = postprocessing_summarization(summary)
summary = find_lapor_and_remove(strings[no], summary)
results.append(summary)
return results
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}: {cleaning(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 = filter_rouge(strings[no], summary, **kwargs)
summary = postprocessing_summarization(summary)
summary = find_lapor_and_remove(strings[no], summary)
results.append(summary)
return results
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()
output = self._mapping.get(decoder)
if not decoder:
raise ValueError(
'mode only supports [`greedy`, `beam`, `nucleus`]')
strings_ = [f'{mode}: {cleaning(string)}' for string in strings]
batch_x = [self._tokenizer.encode(string) + [1] for string in strings_]
batch_x = padding_sequence(batch_x)
p = self._sess.run(output,
feed_dict={
self._X: batch_x,
self._top_p: top_p
}).tolist()
results = []
for no, r in enumerate(p):
summary = self._tokenizer.decode(r)
if postprocess:
summary = filter_rouge(strings[no], summary, **kwargs)
summary = postprocessing_summarization(summary)
summary = find_lapor_and_remove(strings[no], summary)
results.append(summary)
return results