DSE Natural Language Processing Fundamentals 2

Question 1

Which technique is used in word2vec to predict surrounding context words given a target word?

Accepted Answer

Skip-gram

Answer

Skip-gram predicts surrounding context words given a center/target word, while CBOW does the opposite.

Question 2

What does the term 'perplexity' measure in the context of language models?

Accepted Answer

How well a probability model predicts a sample

Answer

Perplexity measures how well a language model predicts a held-out sample — lower perplexity indicates a better model.

Question 3

In transformer architectures, what is the purpose of positional encoding?

Accepted Answer

To inject sequence order information since attention is permutation-invariant

Answer

Self-attention has no inherent notion of order, so positional encodings are added to embeddings to convey token position.

Question 4

Which evaluation metric is most appropriate for machine translation tasks?

Accepted Answer

BLEU score

Answer

BLEU (Bilingual Evaluation Understudy) measures n-gram overlap between generated translations and reference translations.

Question 5

What is the main advantage of subword tokenization methods like Byte-Pair Encoding (BPE) over word-level tokenization?

Accepted Answer

Handles out-of-vocabulary words more gracefully

Answer

BPE breaks rare and unknown words into subword units, reducing out-of-vocabulary issues while keeping common words intact.

DSE - Data Science Practice Test