Attività di generazione di sequenze

Natural Language Processing (NLP) in Python

Fouad Trad

Machine Learning Engineer

Generazione di sequenze

  • Genera nuovo testo da un input dato
  • Include task come:
    • Riassunto testuale
    • Traduzione testuale
    • Language modeling

GIF di una matita che scrive frasi su un foglio.

Natural Language Processing (NLP) in Python

Riassunto testuale

  • Condensa documenti lunghi in versioni brevi con i punti chiave
  • Utile con:
    • Articoli di news lunghi
    • Articoli scientifici
    • Report
    • Email

Immagine con una pila di libri e un documento di riepilogo generato da essi.

Natural Language Processing (NLP) in Python

Pipeline di riassunto testuale

from transformers import pipeline

summarizer = pipeline(task="summarization", model="cnicu/t5-small-booksum")


text = """The Amazon rainforest, often referred to as the "lungs of the Earth," is one of the most 
biologically diverse regions in the world. Spanning over nine countries in South America, the majority 
of the forest lies in Brazil. It is home to an estimated 390 billion individual trees, divided into 
16,000 different species. The rainforest plays a critical role in regulating the global climate by 
absorbing vast amounts of carbon dioxide and producing oxygen."""


result = summarizer(text)

print(result)

[{'summary_text': 'the Amazon rainforest is one of the most biologically diverse regions in the world. 
The majority of the forest lies in Brazil. The rainforest plays a critical role in regulating the 
global climate by absorbing vast amounts of carbon dioxide and producing oxygen.'}]
Natural Language Processing (NLP) in Python

Traduzione testuale

  • Converte testo da una lingua a un’altra
  • Cruciale in app multilingue:
    • Siti internazionali
    • Strumenti di supporto clienti

Immagine che mostra un testo tradotto dall’inglese (Good morning) al francese (Bonjour).

Natural Language Processing (NLP) in Python

Pipeline di traduzione del testo

translator = pipeline(task="translation", model="Helsinki-NLP/opus-mt-en-fr")


sentence = "The rainforest helps regulate the Earth's climate."

result = translator(sentence)

print(result)

[{'translation_text': 'La forêt tropicale aide à réguler le climat de la Terre.'}]
Natural Language Processing (NLP) in Python

Language modeling

  • Predice le prossime parole da un prompt dato
  • Base per molte applicazioni:
    • Autocompletamento
    • Generazione di storie
    • Risposte chatbot

Immagine che mostra come funziona il language modeling: si dà un prompt alla macchina che genera il testo.

Natural Language Processing (NLP) in Python

Pipeline di language modeling

generator = pipeline(task="text-generation", model="distilgpt2")


prompt = "Once upon a time,"

result = generator(prompt, max_length=30, num_return_sequences=3)

print(result)

[{'generated_text': "Once upon a time, my life wasn't so good, I kept my things tidy. The 
                     more time I spend with my children the more ..."}, 
 {'generated_text': 'Once upon a time, we began a process of finding the right answers to 
                     some big questions," said Jim Pelterer, a lecturer at the 
                     University...'}, 
 {'generated_text': 'Once upon a time, a man came along and took in the city, and found out 
                     that a strange woman had just walked in and was dancing about...'}]
Natural Language Processing (NLP) in Python

Alleniamoci!

Natural Language Processing (NLP) in Python

Preparing Video For Download...