DSE Natural Language Processing Fundamentals 5

Question 1

What distinguishes zero-shot classification from few-shot classification in NLP?

Accepted Answer

Zero-shot provides no examples; few-shot provides a small number of examples in the prompt

Answer

Zero-shot classification relies only on task descriptions or label names, while few-shot provides a handful of labeled examples in the input.

Question 2

Which NLP task involves identifying the grammatical role of each word in a sentence, such as noun or verb?

Accepted Answer

Part-of-speech tagging

Answer

Part-of-speech tagging assigns grammatical categories (noun, verb, adjective, etc.) to each token in a sentence.

Question 3

What is the key advantage of using pre-trained contextual embeddings (like those from BERT) over static word embeddings (like word2vec)?

Accepted Answer

They produce different representations for the same word in different contexts

Answer

Contextual embeddings dynamically encode a word's meaning based on its surrounding context, addressing polysemy that static embeddings cannot.

Question 4

In text classification with imbalanced classes, which strategy is most appropriate?

Accepted Answer

Use class-weighted loss or oversample the minority class

Answer

Class-weighted loss or oversampling corrects the model's bias toward the majority class when training data is imbalanced.

Question 5

What is the purpose of the 'CLS' token in BERT-style models?

Accepted Answer

To serve as an aggregate sequence representation for classification tasks

Answer

The [CLS] token is prepended to inputs, and its final hidden state is used as a pooled sentence-level representation for downstream classification.

DSE - Data Science Practice Test