bert extractive summarizer
Small Bug
Dieses Repo ist die Verallgemeinerung des Repo des Vorlesungs-Abläufers. Dieses Tool verwendet die Suggingface Pytorch Transformers Library, um extraktive Zusammenfassungen durchzuführen. Dies funktioniert, indem zuerst die Sätze einbettet und dann ein Clustering -Algorithmus ausgeführt wird und die Sätze gefunden wird, die den Zentroiden des Clusters am nächsten stehen. Diese Bibliothek verwendet auch Coreference -Techniken, wobei die Bibliothek https://github.com/huggingface/neuralcoref in Zusammenfassungen, die mehr Kontext benötigen, auflösen. Die Gierigkeit der Neuralcoref -Bibliothek kann in der CoreferenceHandler -Klasse optimiert werden.
Zum Zeitpunkt der neuesten Version von Bert-Extractive-Sumarizer wird CUDA standardmäßig verwendet, wenn eine GPU verfügbar ist.
Papier: https://arxiv.org/abs/1906.04165
Destill Bert Summar -Demo
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 )Die Anzahl der Sätze kann als Verhältnis oder als Ganzzahl geliefert werden. Beispiele finden Sie unten.
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 Sie können auch die Zusammenbrettung des Zusammenfassungsbettendings zum Clustering verkaufen. Ein einfaches Beispiel ist unten.
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 )Man kann Sätze Bert mit Bert-extraktiven Sumarisator mit der neuesten Version verwenden. Es basiert auf dem Papier hier: https://arxiv.org/abs/1908.10084, und die Bibliothek hier: https://www.sbert.net/. Um zu beginnen, installieren Sie zuerst Sbert:
pip install -U sentence-transformers
Dann ist ein einfaches Beispiel Folgendes:
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 )Es ist erwähnenswert, dass alle Funktionen, die Sie mit der Hauptübersichtsklasse machen können, auch mit Sbert zu tun haben.
Sie können auch die Einbettungen der Zusammenfassung abrufen. Beispiele sind unten:
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. Stellen Sie zunächst sicher, dass Sie NeuralCoref und Spacy installiert haben. Es ist erwähnenswert, dass NeuralCoref nicht mit Spacy> 0.2.1 funktioniert.
pip install spacy
pip install transformers # > 4.0.0
pip install neuralcoref
python -m spacy download en_core_web_mdFühren Sie Folgendes aus:
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.
"""Ab der Bert-extraktiven Sumarisator-Version 0.7.1 können Sie den Ellbogen auch berechnen, um den optimalen Cluster zu bestimmen. Nachfolgend zeigt ein Beispiel Beispiel für das Abrufen der Inertienliste.
from summarizer import Summarizer
body = 'Your Text here.'
model = Summarizer ()
res = model . calculate_elbow ( body , k_max = 10 )
print ( res )Sie können auch die optimale Anzahl von Sätzen mit Ellbogen mit dem folgenden Algorithmus finden.
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.
)
Es gibt einen bereitgestellten Flask -Service und eine entsprechende Dockerfile. Das Ausführen des Dienstes ist einfach und kann durch die Makefile mit den beiden Befehlen erfolgen:
make docker-service-build
make docker-service-run
Dadurch wird das Bert-Base-Bekanntheitsmodell verwendet, das eine kleine Darstellung aufweist. Der Docker -Lauf akzeptiert auch eine Vielzahl von Argumenten für benutzerdefinierte und verschiedene Modelle. Dies kann durch einen Befehl wie:
docker build -t summary-service -f Dockerfile.service ./
docker run --rm -it -p 5000:5000 summary-service:latest -model bert-large-uncased
Andere Argumente können ebenfalls an den Server übergeben werden. Im Folgenden enthält die Liste der verfügbaren Argumente.
Sobald der Dienst ausgeführt wird, können Sie einen Zusammenfassungsbefehl unter http://localhost:5000/summarize . Dieser Endpunkt akzeptiert einen Text/eine einfache Eingabe, die den Text darstellt, den Sie zusammenfassen möchten. Parameter können auch als Anforderungsargumente übergeben werden. Die akzeptierten Argumente sind:
Ein Beispiel für eine Anfrage ist Folgendes:
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."
}
