def __init__(self,
model: str = 'bert-large-uncased',
custom_model: PreTrainedModel = None,
custom_tokenizer: PreTrainedTokenizer = None,
hidden: Union[List[int], int] = -2,
reduce_option: str = 'mean',
sentence_handler: SentenceHandler = SentenceHandler(),
random_state: int = 12345,
hidden_concat: bool = False):
"""
This is the parent Bert Summarizer model. New methods should implement this class.
:param model: This parameter is associated with the inherit string parameters from the transformers library.
:param custom_model: If you have a pre-trained model, you can add the model class here.
:param custom_tokenizer: If you have a custom tokenizer, you can add the tokenizer here.
:param hidden: This signifies which layer(s) of the BERT model you would like to use as embeddings.
:param reduce_option: Given the output of the bert model, this param determines how you want to reduce results.
:param sentence_handler: The handler to process sentences. If want to use coreference, instantiate and pass.
CoreferenceHandler instance
:param random_state: The random state to reproduce summarizations.
:param hidden_concat: Whether or not to concat multiple hidden layers.
"""
np.random.seed(random_state)
self.model = BertParent(model, custom_model, custom_tokenizer)
self.hidden = hidden
self.reduce_option = reduce_option
self.sentence_handler = sentence_handler
self.random_state = random_state
self.hidden_concat = hidden_concat
def __init__(self,
model: str = 'bert-large-uncased',
custom_model: PreTrainedModel = None,
custom_tokenizer: PreTrainedTokenizer = None,
hidden: int = -2,
reduce_option: str = 'mean',
greedyness: float = 0.45,
language=English,
random_state: int = 12345):
"""
This is the parent Bert Summarizer model. New methods should implement this class
:param model: This parameter is associated with the inherit string parameters from the transformers library.
:param custom_model: If you have a pre-trained model, you can add the model class here.
:param custom_tokenizer: If you have a custom tokenizer, you can add the tokenizer here.
:param hidden: This signifies which layer of the BERT model you would like to use as embeddings.
:param reduce_option: Given the output of the bert model, this param determines how you want to reduce results.
:param greedyness: associated with the neuralcoref library. Determines how greedy coref should be.
:param language: Which language to use for training.
:param random_state: The random state to reproduce summarizations.
"""
np.random.seed(random_state)
self.model = BertParent(model, custom_model, custom_tokenizer)
self.hidden = hidden
self.reduce_option = reduce_option
self.nlp = language()
self.random_state = random_state
self.nlp.add_pipe(self.nlp.create_pipe('sentencizer'))
neuralcoref.add_to_pipe(self.nlp, greedyness=greedyness)
def PreProcessor(body, summary_length, min_length: int = 40):
model = BertParent('bert-large-uncased')
algorithm = 'kmeans'
sentence_handler = SentenceHandler()
random_state = 12345
sentences = sentence_handler(body, min_length=40, max_length=600)
print(len(sentences))
if sentences:
#...hidden contains n*1024 matrix as word embeddings returned by BERT model where n is number of sentences
hidden = model(sentences)
#...we call k-means algorithm and pass the word embeddings done by the BERT model
hidden_args = cluster(hidden, algorithm, random_state, summary_length)
sentences = [sentences[j] for j in hidden_args]
return ' '.join(sentences)
def create_embedding_vector(centroid_words):
model = BertParent('bert-large-uncased')
hidden = model(centroid_words)
return hidden