bert extractive summarizer
Small Bug
このレポは、講義とマリザーのリポジトリの一般化です。このツールは、Huggingface Pytorch Transformersライブラリを使用して、抽出的な要約を実行します。これは、最初に文を埋め込み、次にクラスタリングアルゴリズムを実行し、クラスターの重心に最も近い文を見つけることで機能します。このライブラリは、https://github.com/huggingface/neuralcorefライブラリを利用して、より多くのコンテキストが必要な要約の単語を解決するコアレファレンステクニックも使用しています。 NeuralCorefライブラリの貪欲さは、CoreferenceHandlerクラスで微調整できます。
Bert-Extractive-Summarizerの最新バージョンの時点で、デフォルトでは、GPUが利用可能な場合はCUDAが使用されます。
論文：https：//arxiv.org/abs/1906.04165
BERT要約デモを蒸留します
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 )文の数は、比率または整数として提供できます。例を以下に示します。
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 また、クラスタリング用の要約埋め込みを連結することもできます。簡単な例を以下に示します。
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 )最新バージョンでは、Bert-Extractive-SummarizerでBertを使用することができます。 https：//arxiv.org/abs/1908.10084、およびここのライブラリ：https://www.sbert.net/の論文に基づいています。開始するには、最初にSbertをインストールします：
pip install -U sentence-transformers
次に、簡単な例は次のとおりです。
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 )メインサマライザークラスでできるすべての機能は、Stbertでもできることに注意してください。
要約の埋め込みを取得することもできます。例は以下にあります：
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. まず、NeuralCorefとSpacyをインストールしたことを確認してください。 NeuralCorefがSpacy> 0.2.1で動作しないことは注目に値します。
pip install spacy
pip install transformers # > 4.0.0
pip install neuralcoref
python -m spacy download en_core_web_md次に、Coreferenceを使用するには、以下を実行します。
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.
"""Bert-Extractive-Summarizerバージョン0.7.1では、肘を計算して最適なクラスターを決定することもできます。以下は、慣性のリストを取得する方法のサンプル例を示しています。
from summarizer import Summarizer
body = 'Your Text here.'
model = Summarizer ()
res = model . calculate_elbow ( body , k_max = 10 )
print ( res )また、次のアルゴリズムを使用して、肘を備えた最適な文を見つけることもできます。
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.
)
提供されたフラスコサービスと対応するDockerFileがあります。サービスの実行はシンプルで、2つのコマンドを使用してMakeFileを使用できます。
make docker-service-build
make docker-service-run
これにより、小さな表現があるBert-Base Uncasedモデルが使用されます。 Docker Runは、カスタムモデルや異なるモデルに関するさまざまな議論も受け入れます。これは、次のようなコマンドを使用して実行できます。
docker build -t summary-service -f Dockerfile.service ./
docker run --rm -it -p 5000:5000 summary-service:latest -model bert-large-uncased
他の引数もサーバーに渡すことができます。以下に、利用可能な引数のリストが含まれています。
サービスが実行されたら、 http://localhost:5000/summarize endpointで要約コマンドを作成できます。このエンドポイントは、要約するテキストを表すテキスト/プレーン入力を受け入れます。パラメーターは、要求引数として渡すこともできます。受け入れられている議論は次のとおりです。
リクエストの例は次のとおりです。
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."
}
