Q71 — AWS AIF-C01 Ch.3

Question 71 of 100 | ← Chapter 3

A data scientist is studying a text generation model that uses embeddings to represent content as vectors. What is the purpose of using embeddings in this context?

• A. Tokenize input text into individual words or subword units
• B. Encode input text into a sequence of numeric tokens
• C. Apply attention mechanisms to input text
• D. Capture semantic relationships between words based on word vector representations ✓

Correct Answer: D. Capture semantic relationships between words based on word vector representations

Explanation

In text generation models, embeddings convert words or phrases into dense numerical vectors that encode semantic and syntactic relationships. This enables the model to understand contextual meaning and improve generation quality and accuracy. Tokenization and numeric token encoding are preprocessing steps; attention mechanisms operate on embeddings but are not the primary purpose of embeddings themselves. Therefore, the core purpose of embeddings is to capture semantic relationships between words.