Classificazione zero-shot dei ticket di supporto

Un'azienda riceve ogni giorno centinaia di ticket di supporto su temi come problemi di fatturazione, difficoltà tecniche e gestione degli account. Smistarli manualmente è inefficiente. Ti è stato chiesto di usare un modello di classificazione zero-shot per categorizzare automaticamente i messaggi in arrivo senza dover addestrare un classificatore personalizzato.

Questo esercizio fa parte del corso

Natural Language Processing (NLP) in Python

Visualizza il corso

Istruzioni dell'esercizio

Crea una pipeline classifier zero-shot usando il modello "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli".
Usala per classificare ticket_text in una delle categorie elencate in candidate_labels.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

from transformers import pipeline

# Initialize the zero-shot classifier
classifier = ____

ticket_text = "I was charged twice for my subscription this month. Can you please refund the extra charge?"
candidate_labels = ["Billing", "Technical Issue", "Account Access"]

# Classify the ticket
result = ____

print(result['labels'])
print(result['scores'])

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Natural Language Processing (NLP) in Python

IntermediárioNível de habilidade

4.8+

Inizia il corso gratis

Learn the essentials of text processing in Natural Language Processing (NLP). Master techniques such as tokenization, stop word and punctuation removal, and text normalization with lowercasing, stemming, and lemmatization to prepare text data for further analysis and insight extraction.

Exercise 1: Introduction to natural language processing Exercise 2: Sentence and word tokenization Exercise 3: NLP workflow Exercise 4: Stop words and punctuation handling Exercise 5: Removing stop words Exercise 6: Removing punctuation Exercise 7: Text normalization techniques Exercise 8: Lowercasing Exercise 9: Stemming Exercise 10: Lemmatization

Transform raw text into powerful numerical features. Create Bag-of-Words and TF-IDF representations to capture word importance across documents, then explore word embeddings like Word2Vec and GloVe to uncover deep semantic patterns. Visualize frequency, relevance, and similarity to bring your text data to life.

Exercise 1: Bag-of-Words representation Exercise 2: Building vocabulary from customer reviews Exercise 3: Transforming text to numbers with BoW Exercise 4: Frequency analysis of product reviews Exercise 5: Visualizing word frequencies Exercise 6: TF-IDF vectorization Exercise 7: TF-IDF representation of product feedback Exercise 8: Comparing BoW and TF-IDF representations Exercise 9: Embeddings Exercise 10: Exploring word relationships with embeddings Exercise 11: Visualizing and comparing word embeddings

Harness the power of pre-trained models to perform advanced text classification tasks. Use Hugging Face pipelines for sentiment analysis, topic classification, and natural language inference. Evaluate semantic similarity and grammatical correctness with state-of-the-art models, all without building anything from scratch.

Exercise 1: Pipeline di Hugging Face per l'analisi del sentimento Exercise 2: Analizzare il sentiment di una recensione Exercise 3: Classificare in batch più recensioni Exercise 4: Confrontare modelli su dati di recensioni etichettati Exercise 5: Zero-shot classification e QNLI Exercise 6: Classificazione zero-shot dei ticket di supporto

Esercizio in corso

Exercise 7: Il testo risponde alla domanda?Exercise 8: Somiglianza tra domande e correttezza grammaticale Exercise 9: Rilevare domande duplicate Exercise 10: Verificare la correttezza grammaticale

Dive into the core of modern NLP applications with token classification and text generation techniques. Learn to extract meaningful entities and grammatical structures using NER and PoS tagging. Master both extractive and abstractive question answering, and explore advanced generation tasks including summarization, translation, and language modeling using Hugging Face pipelines.

Exercise 1: Token classification Exercise 2: Identifying named entities in news headlines Exercise 3: Part of Speech tagging for text analysis Exercise 4: Question answering Exercise 5: Answering questions from product descriptions Exercise 6: Generating natural answers with abstractive QA Exercise 7: Sequence generation tasks Exercise 8: Summarizing news articles for quick insights Exercise 9: Translating customer reviews to French Exercise 10: Building a search completion system Exercise 11: Congratulations