Zero-shot classification and QNLI

Natural Language Processing (NLP) in Python

Fouad Trad

Machine Learning Engineer

Zero-shot classification

Allows model to assign text to labels it hasn't seen before
Uses natural language prediction get the output
Useful for:
- Content tagging
- Customer support
- Filtering news articles

Image showing a text "The national football team won the cup yesterday" that needs to be classified according to three categories: sports, technology, and health.

Zero-shot classification pipeline

from transformers import pipeline

zero_shot_classifier = pipeline(

  task="zero-shot-classification",

  model="MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli"
)

text = "The national football team won the cup yesterday."

candidate_labels = ["sports", "technology", "health"]

result = zero_shot_classifier(text, candidate_labels)

print(result)

{'sequence': 'The national football team won the cup yesterday.',
 'labels': ['sports', 'technology', 'health'], 
 'scores': [0.9948731064796448, 0.0029330444522202015, 0.002193822991102934]}

Question natural language inference (QNLI)

Determines whether the answer to a question can be found in a passage
Useful for:
- Document search
- Chatbots
- Information retrieval

Image showing that QNLI receives a passage and a question and returns a score.

QNLI pipeline

from transformers import pipeline

qnli_pipeline = pipeline(
    task="text-classification", 
    model="cross-encoder/qnli-electra-base"
    )

passage = "Penguins are found primarily in the Southern Hemisphere."

question = "Where do penguins live?"

result = qnli_pipeline({"text": question, "text_pair": passage})

print(result)

{'label': 'LABEL_0', 'score': 0.9951545000076294}

QNLI pipeline

from transformers import pipeline
qnli_pipeline = pipeline(
    task="text-classification", 
    model="cross-encoder/qnli-electra-base"
    )
passage = "Penguins are found primarily in the Southern Hemisphere."
question = "What is the capital of Paris?"
result = qnli_pipeline({"text": question, "text_pair": passage})
print(result)

{'label': 'LABEL_0', 'score': 0.008907231502234936}

Let's practice!

Natural Language Processing (NLP) in Python