1.
What is the key difference between encoding and embedding?
Select the correct answer.
Encoding is the broader term for converting data to numbers. Embedding is a specific kind of encoding that uses neural networks or transformers to preserve semantic meaning and context.
2.
What does the following code return: model.encode(['Hello world'])?
Select the correct answer.
SentenceTransformer's encode() method returns a numpy array representing the embedding vector for the input text. For a single sentence, you get one vector (a 1D array of floats with as many elements as the model's output dimensions).
3.
Which of the following is NOT a characteristic of embeddings?
Select the correct answer.
Static (fixed) vectors per word is a limitation of classical models like Word2Vec, NOT a characteristic of modern transformer-based embeddings. Modern embeddings are contextual — the same word gets different vectors in different contexts.
