bert extractive summarizer
Small Bug
Este repositorio es la generalización del repositorio de sumarizador de conferencias. Esta herramienta utiliza la biblioteca Huggingface Pytorch Transformers para ejecutar resúmenes de extractivos. Esto funciona primero incrustando las oraciones, luego ejecutando un algoritmo de agrupación, encontrando las oraciones más cercanas a los centroides del clúster. Esta biblioteca también utiliza técnicas de coreferencia, utilizando la biblioteca https://github.com/huggingface/neuralcoref para resolver palabras en resúmenes que necesitan más contexto. La codicia de la biblioteca NeuralCoref se puede ajustar en la clase CoreFerferantHandler.
A partir de la versión más reciente de Bert-Extractive-Summarizer, de forma predeterminada, se utiliza CUDA si hay una GPU disponible.
Documento: https://arxiv.org/abs/1906.04165
Demo de resumen de Bert Bert
pip install bert-extractive-summarizer from summarizer import Summarizer
body = 'Text body that you want to summarize with BERT'
body2 = 'Something else you want to summarize with BERT'
model = Summarizer ()
model ( body )
model ( body2 )El número de oraciones se puede suministrar como una relación o un entero. Se proporcionan ejemplos a continuación.
from summarizer import Summarizer
body = 'Text body that you want to summarize with BERT'
model = Summarizer ()
result = model ( body , ratio = 0.2 ) # Specified with ratio
result = model ( body , num_sentences = 3 ) # Will return 3 sentences También puede concatir los incrustaciones de resumen para la agrupación. Un ejemplo simple está a continuación.
from summarizer import Summarizer
body = 'Text body that you want to summarize with BERT'
model = Summarizer ( 'distilbert-base-uncased' , hidden = [ - 1 , - 2 ], hidden_concat = True )
result = model ( body , num_sentences = 3 )Uno puede usar la oración Bert con Bert-Extractive-Summarizer con la versión más reciente. Se basa en el documento aquí: https://arxiv.org/abs/1908.10084, y la biblioteca aquí: https://www.sbert.net/. Para comenzar, primero instale sbert:
pip install -U sentence-transformers
Entonces un ejemplo simple es el siguiente:
from summarizer . sbert import SBertSummarizer
body = 'Text body that you want to summarize with BERT'
model = SBertSummarizer ( 'paraphrase-MiniLM-L6-v2' )
result = model ( body , num_sentences = 3 )Vale la pena señalar que todas las características que puede hacer con la clase principal de resumen, también puede hacer con Sbert.
También puede recuperar los incrustaciones de la resumen. Los ejemplos están a continuación:
from summarizer import Summarizer
body = 'Text body that you want to summarize with BERT'
model = Summarizer ()
result = model . run_embeddings ( body , ratio = 0.2 ) # Specified with ratio.
result = model . run_embeddings ( body , num_sentences = 3 ) # Will return (3, N) embedding numpy matrix.
result = model . run_embeddings ( body , num_sentences = 3 , aggregate = 'mean' ) # Will return Mean aggregate over embeddings. Primero asegúrese de haber instalado NeuralCoref y Spacy. Vale la pena señalar que NeuralCoref no funciona con Spacy> 0.2.1.
pip install spacy
pip install transformers # > 4.0.0
pip install neuralcoref
python -m spacy download en_core_web_mdLuego, para usar CoreFeference, ejecute lo siguiente:
from summarizer import Summarizer
from summarizer . text_processors . coreference_handler import CoreferenceHandler
handler = CoreferenceHandler ( greedyness = .4 )
# How coreference works:
# >>>handler.process('''My sister has a dog. She loves him.''', min_length=2)
# ['My sister has a dog.', 'My sister loves a dog.']
body = 'Text body that you want to summarize with BERT'
body2 = 'Something else you want to summarize with BERT'
model = Summarizer ( sentence_handler = handler )
model ( body )
model ( body2 ) from transformers import *
# Load model, model config and tokenizer via Transformers
custom_config = AutoConfig . from_pretrained ( 'allenai/scibert_scivocab_uncased' )
custom_config . output_hidden_states = True
custom_tokenizer = AutoTokenizer . from_pretrained ( 'allenai/scibert_scivocab_uncased' )
custom_model = AutoModel . from_pretrained ( 'allenai/scibert_scivocab_uncased' , config = custom_config )
from summarizer import Summarizer
body = 'Text body that you want to summarize with BERT'
body2 = 'Something else you want to summarize with BERT'
model = Summarizer ( custom_model = custom_model , custom_tokenizer = custom_tokenizer )
model ( body )
model ( body2 ) from summarizer import Summarizer
body = '''
The Chrysler Building, the famous art deco New York skyscraper, will be sold for a small fraction of its previous sales price.
The deal, first reported by The Real Deal, was for $150 million, according to a source familiar with the deal.
Mubadala, an Abu Dhabi investment fund, purchased 90% of the building for $800 million in 2008.
Real estate firm Tishman Speyer had owned the other 10%.
The buyer is RFR Holding, a New York real estate company.
Officials with Tishman and RFR did not immediately respond to a request for comments.
It's unclear when the deal will close.
The building sold fairly quickly after being publicly placed on the market only two months ago.
The sale was handled by CBRE Group.
The incentive to sell the building at such a huge loss was due to the soaring rent the owners pay to Cooper Union, a New York college, for the land under the building.
The rent is rising from $7.75 million last year to $32.5 million this year to $41 million in 2028.
Meantime, rents in the building itself are not rising nearly that fast.
While the building is an iconic landmark in the New York skyline, it is competing against newer office towers with large floor-to-ceiling windows and all the modern amenities.
Still the building is among the best known in the city, even to people who have never been to New York.
It is famous for its triangle-shaped, vaulted windows worked into the stylized crown, along with its distinctive eagle gargoyles near the top.
It has been featured prominently in many films, including Men in Black 3, Spider-Man, Armageddon, Two Weeks Notice and Independence Day.
The previous sale took place just before the 2008 financial meltdown led to a plunge in real estate prices.
Still there have been a number of high profile skyscrapers purchased for top dollar in recent years, including the Waldorf Astoria hotel, which Chinese firm Anbang Insurance purchased in 2016 for nearly $2 billion, and the Willis Tower in Chicago, which was formerly known as Sears Tower, once the world's tallest.
Blackstone Group (BX) bought it for $1.3 billion 2015.
The Chrysler Building was the headquarters of the American automaker until 1953, but it was named for and owned by Chrysler chief Walter Chrysler, not the company itself.
Walter Chrysler had set out to build the tallest building in the world, a competition at that time with another Manhattan skyscraper under construction at 40 Wall Street at the south end of Manhattan. He kept secret the plans for the spire that would grace the top of the building, building it inside the structure and out of view of the public until 40 Wall Street was complete.
Once the competitor could rise no higher, the spire of the Chrysler building was raised into view, giving it the title.
'''
model = Summarizer ()
result = model ( body , min_length = 60 )
full = '' . join ( result )
print ( full )
"""
The Chrysler Building, the famous art deco New York skyscraper, will be sold for a small fraction of its previous sales price.
The building sold fairly quickly after being publicly placed on the market only two months ago.
The incentive to sell the building at such a huge loss was due to the soaring rent the owners pay to Cooper Union, a New York college, for the land under the building.'
Still the building is among the best known in the city, even to people who have never been to New York.
"""A partir de la versión 0.7.1 de Bert-Extractive-Summarizer, también puede calcular el codo para determinar el clúster óptimo. A continuación muestra un ejemplo de muestra en cómo recuperar la lista de inercias.
from summarizer import Summarizer
body = 'Your Text here.'
model = Summarizer ()
res = model . calculate_elbow ( body , k_max = 10 )
print ( res )También puede encontrar el número óptimo de oraciones con el codo utilizando el siguiente algoritmo.
from summarizer import Summarizer
body = 'Your Text here.'
model = Summarizer ()
res = model . calculate_optimal_k ( body , k_max = 10 )
print ( res ) model = Summarizer(
model: This gets used by the hugging face bert library to load the model, you can supply a custom trained model here
custom_model: If you have a pre-trained model, you can add the model class here.
custom_tokenizer: If you have a custom tokenizer, you can add the tokenizer here.
hidden: Needs to be negative, but allows you to pick which layer you want the embeddings to come from.
reduce_option: It can be 'mean', 'median', or 'max'. This reduces the embedding layer for pooling.
sentence_handler: The handler to process sentences. If want to use coreference, instantiate and pass CoreferenceHandler instance
)
model(
body: str # The string body that you want to summarize
ratio: float # The ratio of sentences that you want for the final summary
min_length: int # Parameter to specify to remove sentences that are less than 40 characters
max_length: int # Parameter to specify to remove sentences greater than the max length,
num_sentences: Number of sentences to use. Overrides ratio if supplied.
)
Hay un servicio de frasco provisto y Dockerfile correspondiente. Ejecutar el servicio es simple y se puede hacer a través de MakeFile con los dos comandos:
make docker-service-build
make docker-service-run
Esto utilizará el modelo Bert-Base-Insiding, que tiene una pequeña representación. El Docker Run también acepta una variedad de argumentos para modelos personalizados y diferentes. Esto se puede hacer a través de un comando como:
docker build -t summary-service -f Dockerfile.service ./
docker run --rm -it -p 5000:5000 summary-service:latest -model bert-large-uncased
Otros argumentos también se pueden pasar al servidor. A continuación incluye la lista de argumentos disponibles.
Una vez que el servicio se está ejecutando, puede hacer un comando de resumen en http://localhost:5000/summarize el punto final. Este punto final acepta un texto/entrada simple que representa el texto que desea resumir. Los parámetros también se pueden aprobar como argumentos de solicitud. Los argumentos aceptados son:
Un ejemplo de una solicitud es el siguiente:
POST http://localhost:5000/summarize?ratio=0.1
Content-type: text/plain
Body:
The Chrysler Building, the famous art deco New York skyscraper, will be sold for a small fraction of its previous sales price.
The deal, first reported by The Real Deal, was for $150 million, according to a source familiar with the deal.
Mubadala, an Abu Dhabi investment fund, purchased 90% of the building for $800 million in 2008.
Real estate firm Tishman Speyer had owned the other 10%.
The buyer is RFR Holding, a New York real estate company.
Officials with Tishman and RFR did not immediately respond to a request for comments.
It's unclear when the deal will close.
The building sold fairly quickly after being publicly placed on the market only two months ago.
The sale was handled by CBRE Group.
The incentive to sell the building at such a huge loss was due to the soaring rent the owners pay to Cooper Union, a New York college, for the land under the building.
The rent is rising from $7.75 million last year to $32.5 million this year to $41 million in 2028.
Meantime, rents in the building itself are not rising nearly that fast.
While the building is an iconic landmark in the New York skyline, it is competing against newer office towers with large floor-to-ceiling windows and all the modern amenities.
Still the building is among the best known in the city, even to people who have never been to New York.
It is famous for its triangle-shaped, vaulted windows worked into the stylized crown, along with its distinctive eagle gargoyles near the top.
It has been featured prominently in many films, including Men in Black 3, Spider-Man, Armageddon, Two Weeks Notice and Independence Day.
The previous sale took place just before the 2008 financial meltdown led to a plunge in real estate prices.
Still there have been a number of high profile skyscrapers purchased for top dollar in recent years, including the Waldorf Astoria hotel, which Chinese firm Anbang Insurance purchased in 2016 for nearly $2 billion, and the Willis Tower in Chicago, which was formerly known as Sears Tower, once the world's tallest.
Blackstone Group (BX) bought it for $1.3 billion 2015.
The Chrysler Building was the headquarters of the American automaker until 1953, but it was named for and owned by Chrysler chief Walter Chrysler, not the company itself.
Walter Chrysler had set out to build the tallest building in the world, a competition at that time with another Manhattan skyscraper under construction at 40 Wall Street at the south end of Manhattan. He kept secret the plans for the spire that would grace the top of the building, building it inside the structure and out of view of the public until 40 Wall Street was complete.
Once the competitor could rise no higher, the spire of the Chrysler building was raised into view, giving it the title.
Response:
{
"summary": "The Chrysler Building, the famous art deco New York skyscraper, will be sold for a small fraction of its previous sales price. The buyer is RFR Holding, a New York real estate company. The incentive to sell the building at such a huge loss was due to the soaring rent the owners pay to Cooper Union, a New York college, for the land under the building."
}
