bert extractive summarizer
Small Bug
Ce dépôt est la généralisation du dépôt de maîtrise de la conférence. Cet outil utilise la bibliothèque de transformateurs Pytorch HuggingFace pour exécuter des résumés extractifs. Cela fonctionne en intégrant d'abord les phrases, puis en exécutant un algorithme de clustering, en trouvant les phrases les plus proches des centroïdes du cluster. Cette bibliothèque utilise également des techniques de coreférence, en utilisant la bibliothèque https://github.com/huggingface/neuralcoref pour résoudre les mots dans des résumés qui ont besoin de plus de contexte. La greffe de la bibliothèque NeuralCoref peut être modifiée dans la classe CoreferenceHandler.
À partir de la version la plus récente de Bert-Extractive-Summizer, par défaut, CUDA est utilisé si un GPU est disponible.
Papier: https://arxiv.org/abs/1906.04165
Démo de résumé de distill 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 )Le nombre de phrases peut être fourni sous forme de rapport ou entier. Des exemples sont fournis ci-dessous.
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 Vous pouvez également concat les intégres de résumé pour le clustering. Un exemple simple est ci-dessous.
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 )On peut utiliser la phrase Bert avec Bert-Extractive-Summizer avec la dernière version. Il est basé sur le document ici: https://arxiv.org/abs/1908.10084, et la bibliothèque ici: https://www.sbert.net/. Pour commencer, installez d'abord Sbert:
pip install -U sentence-transformers
Alors un exemple simple est le suivant:
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 )Il convient de noter que toutes les fonctionnalités que vous pouvez faire avec la classe de résumé principale, vous pouvez également faire avec SBERT.
Vous pouvez également récupérer les intérêts de la résumé. Des exemples sont ci-dessous:
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. Assurez-vous d'abord que vous avez installé NeuralCoref et Spacy. Il convient de noter que NeuralCoref ne fonctionne pas avec Spacy> 0.2.1.
pip install spacy
pip install transformers # > 4.0.0
pip install neuralcoref
python -m spacy download en_core_web_mdEnsuite, pour utiliser Coreference, exécutez ce qui suit:
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.
"""En ce qui concerne la version 0.7.1 de Bert-Extractive-Summarizer, vous pouvez également calculer le coude pour déterminer le cluster optimal. Vous trouverez ci-dessous un exemple d'exemple dans la façon de récupérer la liste des inertias.
from summarizer import Summarizer
body = 'Your Text here.'
model = Summarizer ()
res = model . calculate_elbow ( body , k_max = 10 )
print ( res )Vous pouvez également trouver le nombre optimal de phrases avec le coude en utilisant l'algorithme suivant.
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.
)
Il y a un service FLASK fourni et DockerFile correspondant. L'exécution du service est simple et peut être effectuée à travers le makefile avec les deux commandes:
make docker-service-build
make docker-service-run
Cela utilisera le modèle de Bert-Base-Scomber, qui a une petite représentation. Le Docker Run accepte également une variété d'arguments pour les modèles personnalisés et différents. Cela peut être fait via une commande telle que:
docker build -t summary-service -f Dockerfile.service ./
docker run --rm -it -p 5000:5000 summary-service:latest -model bert-large-uncased
D'autres arguments peuvent également être transmis au serveur. Vous trouverez ci-dessous la liste des arguments disponibles.
Une fois le service en cours d'exécution, vous pouvez faire une commande de résumé au http://localhost:5000/summarize le point de terminaison. Ce point de terminaison accepte une entrée texte / simple qui représente le texte que vous souhaitez résumer. Les paramètres peuvent également être adoptés comme arguments de demande. Les arguments acceptés sont:
Un exemple de demande est le suivant:
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."
}
